Compare LLM Models

Select 2-5 models to compare side by side.

Select models to compare 0 / 5 selected

🤖 Qwen3.6-27B-FP8 🤖 Qwen3-8B 🤖 Qwen3.6-35B-A3B-NVFP4 🤖 Qwen2.5-7B-Instruct 🤖 gemma-4-31B-it 🤖 OTel-2.0-LLM-31B-IT farbodtavakkoli 🤖 Qwen3-Swallow-32B-RL-v0.2-AWQ-INT4 tokyotech-llm 🤖 gemma-4-31B-it-uncensored-heretic-GGUF llmfan46 🤖 Qwen3-Coder-30B-A3B-Instruct-GGUF 🤖 Qwen3-VL-8B-Instruct 🤖 gemma-4-26B-A4B-it 🤖 Qwen3.6-35B-A3B-FP8 🤖 Qwen3.5-9B 🤖 Qwen2.5-VL-7B-Instruct 🤖 Qwen2.5-3B-Instruct 🤖 OTel-LLM-27B-IT farbodtavakkoli 🤖 Llama-3.1-Swallow-8B-Instruct-v0.5 tokyotech-llm 🤖 OTel-LLM-E4B-IT farbodtavakkoli 🤖 Qwen2.5-1.5B-Instruct 🤖 Qwen3-0.6B 🤖 gpt2 🤖 llm-jp-3-150m llm-jp 🤖 opt-125m 🤖 tiny-Qwen2ForCausalLM-2.5 🤖 gemma-4-31B-it-uncensored-heretic llmfan46 🤖 Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-GGUF llmfan46 🤖 Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-GPTQ-Int4 llmfan46 🤖 deepseek-llm-7b-base deepseek-ai 🤖 Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF llmfan46 🤖 Tiny-LLM arnir0 🤖 JoyAI-LLM-Flash-MXFP8-last-6-BF16 zianglih 🤖 gemma-4-26B-A4B-it-ultra-uncensored-heretic-GGUF llmfan46 🤖 deepseek-llm-7b-chat deepseek-ai 🤖 Qwen3-VL-32B-Instruct-ultra-uncensored-heretic-GGUF llmfan46 🤖 Ornith-1.0-35B-uncensored-heretic-GGUF llmfan46 🤖 LongCat-Flash-Lite-Uncensored-Heretic-Native-MTP-Preserved-GGUF llmfan46 🤖 llm-jp-4-33b-thinking llm-jp 🤖 gemma-4-26B-A4B-it-qat-q4_0-uncensored-heretic-NVFP4 llmfan46 🤖 Qwen3.6-35B-A3B-uncensored-heretic-GGUF llmfan46 🤖 Mizan-27B-Turkish-Legal-LLM-Q4_K_M-GGUF AlicanKiraz0 🤖 Qwythos-9B-Claude-Mythos-5-1M-uncensored-heretic-GGUF llmfan46 🤖 Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-NVFP4-Experts-Only-GGUF llmfan46 🤖 Cybersecurity-BaronLLM_Offensive_Security_LLM_Q6_K_GGUF AlicanKiraz0 🤖 Youtu-LLM-2B tencent 🤖 AI21-Jamba2-Mini-Ultra-Uncensored-Heretic-GGUF llmfan46 🤖 gemma-4-26B-A4B-it-uncensored-heretic-GGUF llmfan46 🤖 dots.llm1.base dots-studio 🤖 Qwen3.6-35B-A3B-uncensored-heretic-GPTQ-Int4 llmfan46 🤖 deepseek-llm-67b-base deepseek-ai 🤖 Llama-3-Swallow-8B-Instruct-v0.1 tokyotech-llm 🤖 Qwen3.6-35B-A3B-uncensored-heretic-NVFP4-Experts-Only-GGUF llmfan46 🤖 Qwen3.5-9B-ultra-uncensored-heretic-GGUF llmfan46 🤖 gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-GGUF llmfan46 🤖 Qwen3-Swallow-32B-RL-v0.2 tokyotech-llm 🤖 llm-jp-3-1.8b llm-jp 🤖 Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved-NVFP4-GGUF llmfan46 🤖 llm-jp-4-8b-instruct llm-jp 🤖 Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GPTQ-Int4 llmfan46 🤖 gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-uncensored-heretic-GGUF llmfan46 🤖 Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4 llmfan46 🤖 Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-NVFP4-GGUF llmfan46 🤖 gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-GGUF llmfan46 🤖 pinkelephant-llm-48b-s pinkelephantlimited 🤖 Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved llmfan46 🤖 Replete-LLM-V2.5-Qwen-14b-GGUF bartowski 🤖 Qwen3.5-35B-A3B-ultra-uncensored-heretic-GGUF llmfan46 🤖 gemma-4-26B-A4B-it-qat-q4_0-uncensored-heretic-GGUF llmfan46 🤖 moxin-llm-7b-GGUF bartowski 🤖 llm-jp-4-8b-thinking llm-jp 🤖 gemma-4-31B-it-qat-q4_0-uncensored-heretic-GGUF llmfan46 🤖 llm-jp-4-33b-thinking-gguf llm-jp 🤖 llm-jp-4-32b-a3b-thinking-gguf llm-jp 🤖 Qwen3-Swallow-8B-RL-v0.2 tokyotech-llm 🤖 Llama-3.1-Swallow-8B-Instruct-v0.3 tokyotech-llm 🤖 Qwen3.5-4B 🤖 Llama-3.2-1B-Instruct 🤖 gpt-oss-20b 🤖 Qwen2.5-0.5B-Instruct 🤖 Llama-3.1-8B-Instruct 🤖 Qwen3-4B 🤖 Qwen3.6-27B 🤖 gpt-oss-120b 🤖 Qwen3.8-27B-FP8 🤖 Qwen3.6-35B-A3B 🤖 Qwen3-32B 🤖 Qwen3.8-27B 🤖 DeepSeek-V4-Flash-0731 🤖 Qwen3-VL-4B-Instruct 🤖 Qwen2.5-7B-Instruct-AWQ 🤖 Qwen2.5-VL-3B-Instruct 🤖 Qwen3-1.7B 🤖 Qwen3-4B-Instruct-2507 🤖 gemma-3-1b-it 🤖 Qwen3.5-2B 🤖 Qwen3-VL-2B-Instruct 🤖 Kimi-K3 🤖 Qwen-72B 🤖 Florence-2-base 🤖 SmolLM2-135M 🤖 DeepSeek-OCR 🤖 GLM-OCR 🤖 DeepSeek-R1 🤖 Gemma-4-31B-IT-NVFP4 🤖 GLM-4.7-Flash 🤖 DeepSeek-V4-Flash 🤖 Meta-Llama-3-8B-Instruct 🤖 GLM-5.2 🤖 Gemma-4-26B-A4B-NVFP4 🤖 SmolVLM2-500M-Video-Instruct 🤖 GLM-5.2-FP8 🤖 phi-2 🤖 gemma-3-4b-it 🤖 DeepSeek-V3.2 🤖 gemma-3-270m 🤖 SmolLM2-135M-Instruct 🤖 Llama-3.2-1B 🤖 diffusiongemma-26B-A4B-it 🤖 gemma-4-31B-it-qat-w4a16-ct 🤖 Mistral-7B-Instruct-v0.2 🤖 GLM-5.2-NVFP4 🤖 NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 🤖 DeepSeek-OCR-2 🤖 DeepSeek-V3-0324 🤖 Llama-3.2-3B-Instruct 🤖 DeepSeek-V3 🤖 NVIDIA-Nemotron-3-Super-120B-A12B-BF16 🤖 DeepSeek-R1-0528-Qwen3-8B 🤖 Cosmos-Reason2-2B 🤖 medgemma-4b-it 🤖 bloomz-560m 🤖 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 🤖 OLMo-2-0425-1B 🤖 gemma-3-12b-it 🤖 NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 🤖 GLM-5-FP8 🤖 Qwen3.5-122B-A10B-NVFP4 🤖 deepseek-coder-7b-instruct-v1.5 🤖 DeepSeek-V4-Pro 🤖 Llama-2-7b-hf 🤖 MiniMax-M2.5-NVFP4 🤖 gemma-2-2b-it 🤖 gemma-4-31B 🤖 Qwen3.6-27B-NVFP4 🤖 DeepSeek-Coder-V2-Lite-Instruct 🤖 gemma-2-9b-it 🤖 Phi-3.5-vision-instruct 🤖 NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 🤖 HunyuanOCR 🤖 Meta-Llama-3-8B 🤖 SmolLM3-3B-Base 🤖 Kimi-K2.6 🤖 phi-4 🤖 Florence-2-large 🤖 Phi-3-mini-4k-instruct 🤖 Llama-3.1-8B 🤖 DeepSeek-R1-Distill-Qwen-32B 🤖 SmolLM3-3B 🤖 SmolVLM-256M-Instruct 🤖 falcon-7b 🤖 NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 🤖 Kimi-K2.5 🤖 Cosmos-Reason2-8B 🤖 Kimi-K2.7-Code-NVFP4 🤖 Llama-3.1-70B-Instruct 🤖 Llama-3.1-405B-FP8 🤖 DeepSeek-R1-Distill-Qwen-14B 🤖 DeepSeek-R1-Distill-Qwen-1.5B 🤖 Qwen3-8B-FP8 🤖 bloom-560m 🤖 Phi-4-mini-instruct 🤖 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 🤖 DeepSeek-V2-Lite-Chat 🤖 deepseek-coder-6.7b-instruct 🤖 Llama-3.3-70B-Instruct 🤖 SmolLM2-360M 🤖 GLM-5.1-FP8 🤖 DeepSeek-R1-Distill-Llama-8B 🤖 DeepSeek-V4-Flash-DSpark 🤖 GLM-5.3-Flash 🤖 Llama-3.2-3B 🤖 DeepSeek-R1-Distill-Qwen-7B 🤖 DeepSeek-V2-Lite 🤖 Mistral-7B-v0.1 🤖 Llama-2-7b-chat-hf 🤖 Kimi-VL-A3B-Instruct 🤖 SmolLM2-1.7B 🤖 SmolLM2-360M-Instruct 🤖 Olmo-3-7B-Instruct 🤖 deepseek-vl2-tiny 🤖 OLMoE-1B-7B-0125-Instruct 🤖 olmOCR-2-7B-1025-FP8 🤖 Llama-4-Scout-17B-16E-Instruct 🤖 Kimi-K2.7-Code 🤖 olmOCR-2-7B-1025 🤖 GLM-4.1V-9B-Thinking 🤖 DeepSeek-V3.1 🤖 DeepSeek-R1-0528 🤖 Llama-Guard-3-8B 🤖 SmolLM2-1.7B-Instruct 🤖 Kimi-Linear-48B-A3B-Instruct 🤖 Mistral-7B-Instruct-v0.1 🤖 SmolVLM2-2.2B-Instruct 🤖 Kimi-K2-Instruct 🤖 OLMoE-1B-7B-0924 🤖 SmolLM-135M 🤖 wildguard 🤖 Meta-Llama-3-70B 🤖 Llama-3.1-405B 🤖 DeepSeek-V4-Pro-0813 🤖 Molmo2-8B 🤖 Llama-2-13b-chat-hf 🤖 GLM-4.5-Air 🤖 Olmo-3-1025-7B 🤖 Llama-3.2-11B-Vision-Instruct 🤖 Llama-3.2-90B-Vision-Instruct 🤖 SmolVLM-500M-Instruct 🤖 GLM-4.6V-Flash 🤖 GLM-4.5 🤖 DeepSeek-R1-Distill-Llama-70B 🤖 DeepSeek-V3.2-Exp 🤖 Llama-Guard-4-12B 🤖 GLM-5.1 🤖 GLM-4.5-Air-FP8 🤖 gpt-oss-safeguard-20b 🤖 Llama-4-Maverick-17B-128E-Instruct-FP8 🤖 OLMo-2-0425-1B-Instruct 🤖 Olmo-3-7B-Think 🤖 Meta-Llama-3-70B-Instruct 🤖 GLM-4.7 🤖 GLM-5 🤖 deepseek-coder-6.7b-base 🤖 SmolLM-1.7B 🤖 Molmo2-4B 🤖 falcon-mamba-tiny-dev 🤖 GLM-5.3 🤖 Falcon-H1-0.5B-Base 🤖 OLMo-2-1124-7B-Instruct 🤖 GLM-4.5V 🤖 falcon-mamba-7b 🤖 Moonlight-16B-A3B-Instruct 🤖 Hy3-preview 🤖 SmolVLM2-256M-Video-Instruct 🤖 bloom-1b7 🤖 OLMo-1B-hf 🤖 Kimi-VL-A3B-Thinking 🤖 Hunyuan-A13B-Instruct 🤖 Molmo2-O-7B 🤖 Llama-3.1-70B 🤖 Olmo-3-7B-Instruct-SFT 🤖 Olmo-3-1125-32B 🤖 Kimi-K2-Thinking 🤖 Hy3-FP8 🤖 Kimi-K2-Instruct-0905 🤖 OLMo-2-1124-7B-SFT 🤖 Yi-6B 🤖 Kimi-VL-A3B-Thinking-2506 🤖 Llama-Guard-3-1B 🤖 GLM-4-9B-0414 🤖 SmolLM-135M-Instruct 🤖 falcon-7b-instruct 🤖 Yi-6B-Chat 🤖 SmolVLM-Instruct 🤖 Yi-34B-Chat 🤖 truthfulqa-truth-judge-llama2-7B 🤖 truthfulqa-info-judge-llama2-7B 🤖 GLM-Z1-32B-0414 🤖 Olmo-Hybrid-7B 🤖 GLM-4.7-FP8 🤖 AutoGLM-Phone-9B 🤖 Llama-2-13b-hf 🤖 Moonlight-16B-A3B 🤖 bloom-3b 🤖 Falcon3-7B-Instruct 🤖 bloom 🤖 GLM-4.6 🤖 Hunyuan-7B-Instruct 🤖 Yi-1.5-9B-Chat 🤖 Falcon-H1-7B-Instruct 🤖 Yi-6B-200K 🤖 Yi-1.5-9B 🤖 Kimi-K2-Base 🤖 SmolLM-360M-Instruct 🤖 Yi-1.5-34B-Chat 🤖 Falcon3-7B-Base 🤖 Falcon3-1B-Instruct 🤖 falcon-40b 🤖 Yi-1.5-6B 🤖 bigscience-small-testing 🤖 Falcon3-1B-Base 🤖 falcon-mamba-7b-instruct 🤖 Hy3 🤖 Llama-4-Maverick-17B-128E-Instruct 🤖 Youtu-LLM-2B 🤖 bloom-1b1 🤖 Falcon-H1-0.5B-Instruct 🤖 SmolLM2-1.7B-Instruct-GGUF 🤖 Falcon-H1-1.5B-Deep-Instruct 🤖 bloom-7b1 🤖 Yi-34B 🤖 Yi-Coder-9B-Chat 🤖 Falcon-H1-3B-Instruct 🤖 Yi-1.5-34B 🤖 Yi-1.5-9B-Chat-16K 🤖 Yi-34B-200K 🤖 Yi-9B 🤖 Yi-9B-200K 🤖 Yi-1.5-34B-Chat-16K 🤖 Yi-Coder-9B 🤖 Yi-1.5-9B-32K 🤖 Yi-1.5-34B-32K 🤖 SmolLM-1.7B-Instruct 🤖 bloomz-7b1 🤖 Falcon3-10B-Instruct 🤖 bloomz-3b 🤖 Falcon3-3B-Instruct 🤖 mt0-small 🤖 SmolLM-360M 🤖 gpt-oss-safeguard-120b 🤖 SmolVLM-Base 🤖 Falcon3-10B-Base 🤖 Yi-1.5-6B-Chat 🤖 falcon-40b-instruct 🤖 Falcon-H1-Tiny-R-0.6B 🤖 falcon-rw-1b 🤖 Falcon3-3B-Base 🤖 falcon-11B 🤖 Falcon-H1R-7B-GGUF 🤖 Kimi-Linear-48B-A3B-Base 🤖 Falcon-H1-1.5B-Base 🤖 Falcon-H1-Tiny-Multilingual-100M-Instruct 🤖 Yi-VL-6B 🤖 bloomz-1b7 🤖 Kimi-Dev-72B 🤖 SmolVLM-500M-Base 🤖 mt0-base 🤖 bloomz-1b1 🤖 bloomz 🤖 mt0-large 🤖 Yi-Coder-1.5B-Chat 🤖 mt0-xl 🤖 circuit-sparsity 🤖 Yi-6B-Chat-4bits 🤖 Yi-VL-34B 🤖 Yi-34B-Chat-8bits 🤖 Yi-34B-Chat-4bits 🤖 Yi-6B-Chat-8bits 🤖 bloom-1b1-intermediate 🤖 bloomz-7b1-mt 🤖 mt0-xxl 🤖 bloom-7b1-petals 🤖 bloom-560m-intermediate 🤖 bloomz-p3 🤖 bloom-7b1-intermediate 🤖 bloom-3b-intermediate 🤖 bloomz-mt 🤖 bloom-1b7-intermediate 🤖 OTel-2.0-LLM-31B-IT 🤖 dolphin-2.9.1-yi-1.5-34b 🤖 Ornith-1.0-9B-GGUF 🤖 pythia-160m 🤖 Kimi-K3-DSpark 🤖 Ornith-1.0-35B-GGUF 🤖 Unlimited-OCR 🤖 Ornith-1.0-35B 🤖 chandra-ocr-2 🤖 Qwen2.5-14B-Instruct 🤖 Qwen3.8-27B-MLX-4bit 🤖 Gemma-4-E4B-Uncensored-HauhauCS-Aggressive 🤖 Qwen3.8-27B-MLX-8bit 🤖 Qwen3.5-27B 🤖 Qwen3.8-27B-MLX-6bit 🤖 Qwen3.8-27B-MLX-5bit 🤖 Qwen3.5-35B-A3B 🤖 Qwen3.5-0.8B 🤖 gemma-4-26B-A4B-it-AWQ-4bit 🤖 Ornith-1.5-9B-GGUF 🤖 Qwen3-30B-A3B 🤖 Qwen2.5-Coder-7B-Instruct 🤖 Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 🤖 Qwen3-VL-8B-Instruct-FP8 🤖 Qwen3-14B-AWQ 🤖 Ornith-1.5-35B-A3B-GGUF 🤖 Qwen2.5-14B-Instruct-AWQ 🤖 llava-1.5-7b-hf 🤖 deepseek-v4-gguf 🤖 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive 🤖 distilgpt2 🤖 Qwen2.5-VL-32B-Instruct-AWQ 🤖 Qwen3.8-27B-Uncensored-GGUF 🤖 Qwen2.5-32B-Instruct 🤖 Qwen2.5-Coder-14B-Instruct 🤖 Ternary-Bonsai-27B-mlx-2bit 🤖 Qwen3.6-27B-AWQ-INT4 🤖 Bonsai-27B-mlx-1bit 🤖 TinyLlama-1.1B-Chat-v1.0 🤖 Qwen2.5-Coder-14B-Instruct-AWQ 🤖 Ornith-1.0-9B 🤖 Qwen3-14B 🤖 Qwen3.5-122B-A10B-FP8 🤖 Qwen3-8B-AWQ 🤖 Huihui-Qwen3.8-27B-abliterated-GGUF 🤖 Qwen3-Coder-Next-FP8 🤖 Qwen2.5-0.5B 🤖 moondream2 🤖 Qwen2.5-Coder-32B-Instruct 🤖 Qwen3-4B-Base 🤖 Qwen3-1.7B-Base 🤖 Qwen2-VL-7B-Instruct-AWQ 🤖 Qwen2-VL-2B-Instruct 🤖 tiny-Qwen3ForCausalLM 🤖 Qwen2.5-VL-7B-Instruct-AWQ 🤖 Qwen3.5-9B-GGUF 🤖 Qwen3-VL-30B-A3B-Instruct-AWQ 🤖 Qwen2.5-VL-32B-Instruct 🤖 OTel-LLM-E4B-IT 🤖 Qwen3.5-2B-Base 🤖 Qwen3.8-27B-NVFP4 🤖 Qwen3-30B-A3B-Instruct-2507 🤖 OpenELM-1_1B-Instruct 🤖 Qwen2.5-Coder-32B-Instruct-AWQ 🤖 gemma-3-27b-it-int4-awq 🤖 OTel-LLM-27B-IT 🤖 Unlimited-OCR-AWQ 🤖 surya-ocr-2 🤖 Qwen3.5-35B-A3B-FP8 🤖 tiny-random-LlamaForCausalLM 🤖 Qwen3.6-35B-A3B-GGUF 🤖 Qwen2-VL-7B-Instruct 🤖 Qwen3.5-9B-AWQ 🤖 Qwen3.6-27B-int4-AutoRound 🤖 Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF 🤖 tiny-gpt2 🤖 granite-4.1-8b 🤖 Qwen3.6-27B-GGUF 🤖 PowerMoE-3b 🤖 Qwen3-4B-Instruct-2507-FP8 🤖 Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF 🤖 MiniMax-M2.7 🤖 Inkling-Small-GGUF 🤖 Qwen3-Coder-30B-A3B-Instruct-FP8 🤖 Qwen3.5-4B-GGUF 🤖 Qwen3.8-27B-AWQ-INT4 🤖 Qwen2.5-1.5B 🤖 gpt2-large 🤖 Qwen3.6-27B-Text-NVFP4-MTP 🤖 Qwen3.6-35B-A3B-abliterated-v4 🤖 gemma-4-26B-A4B-it-GGUF 🤖 Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V12-GGUF 🤖 Qwen3.5-122B-A10B 🤖 Qwen3-0.6B-Base 🤖 Muse-Glimmer-30B-GGUF 🤖 gemma-4-31B-it-FP8-block 🤖 Qwen2-1.5B-Instruct 🤖 Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit 🤖 tiny-Qwen2_5_VLForConditionalGeneration 🤖 Qwen3.8-27B-GGUF 🤖 surya-ocr-2-gguf 🤖 Rax-4.5 🤖 LFM2.5-2.6B-GGUF 🤖 Qwen3.6-27B-MTP-GGUF 🤖 Qwen3-VL-235B-A22B-Instruct 🤖 Huihui-Qwen3.6-27B-abliterated-AWQ-MTP 🤖 Qwen2-0.5B 🤖 Qwen2.5-Math-1.5B 🤖 Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF 🤖 pythia-70m-deduped 🤖 tiny-GptOssForCausalLM 🤖 SmolLM-1.7B-Instruct-quantized.w4a16 🤖 Ornith-1.0-35B-FP8 🤖 MiniCPM5-1B 🤖 gpt-neox-20b 🤖 Qwen3.6-35B-A3B-AWQ-4bit 🤖 Qwen3-Coder-30B-A3B-Instruct 🤖 Qwen3.6-27B-AWQ 🤖 Qwen2.5-Coder-1.5B-Instruct 🤖 Qwen3-VL-30B-A3B-Instruct-FP8 🤖 llama-3.3-70b-instruct-awq 🤖 tiny-random-OPTForCausalLM 🤖 Qwen3.8-27B-OBLITERATED 🤖 Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF 🤖 Qwen3.5-4B-AWQ-4bit 🤖 Qwen3-30B-A3B-Instruct-2507-AWQ-4bit 🤖 Qwen3.6-35B-A3B-AWQ 🤖 pythia-160m-deduped 🤖 Qwen3.6-35B-A3B-GPTQ-Int4 🤖 gemma-4-26B-A4B-it-FP8-dynamic 🤖 UI-TARS-1.5-7B 🤖 GOT-OCR2_0 🤖 Qwen3.5-397B-A17B-FP8 🤖 Qwen3-32B-AWQ 🤖 gemma-4-26B-A4B-it-qat-GGUF 🤖 tiny-Qwen3MoeForCausalLM 🤖 Qwen3-30B-A3B-Instruct-2507-FP8 🤖 endless-frontier_BigBang-v1-GGUF 🤖 Qwen3.6-35B-A3B-heretic-NVFP4 🤖 InternVL2-2B 🤖 gemma-3-27b-it-GPTQ-4b-128g 🤖 Qwen3-VL-32B-Instruct 🤖 MiniCPM-SALA-AWQ-8bit 🤖 Ternary-Bonsai-27B-gguf 🤖 Apertus-8B-Instruct-2509 🤖 POCKET-35B-GGUF 🤖 gemma-4-31B-it-qat-GGUF 🤖 Muse-Glimmer-30B 🤖 Qwen3.5-9B-MLX-4bit 🤖 Qwen2.5-Coder-7B-Instruct-AWQ 🤖 Qwen2.5-32B-Instruct-AWQ 🤖 Qwen2.5-7B 🤖 Kimi-K3-GGUF 🤖 InternVL2-1B 🤖 llava-onevision-qwen2-0.5b-ov-hf 🤖 Qwen3-14B-Base 🤖 Qwen2.5-32B-Instruct-GPTQ-Int4 🤖 Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF 🤖 Qwen3.5-9B-MLX-8bit 🤖 gemma-4-E2B-it-GGUF 🤖 gemma-4-E4B-it-GGUF 🤖 Qwen2.5-Coder-7B 🤖 gemma-2-9b-it-AWQ-INT4 🤖 XYZAILab_XYZ-Aquila-mini-GGUF 🤖 gpt-oss-20b-GGUF 🤖 Bonsai-27B-gguf 🤖 Qwen2.5-3B-Instruct-AWQ 🤖 MiniCPM-V-4.6 🤖 Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 🤖 japanese-gpt-neox-small 🤖 macbert4csc-base-chinese 🤖 Qwen3.6-27B-MLX-8bit 🤖 inkling-GGUF 🤖 Qwen3.6-35B-A3B-MTP-GGUF 🤖 gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF 🤖 Qwythos-9B-v2-GGUF 🤖 Qwen3.6-27B-MLX-4bit 🤖 tiny-random-Llama-3 🤖 Dolphin-Mistral-24B-Venice-Edition 🤖 Ornith-1.5-397B-GGUF 🤖 gpt-neo-125m 🤖 gemma-4-26B-A4B-it-qat-q4_0-gguf 🤖 Qwen3-VL-32B-Instruct-FP8 🤖 Qwen3.6-27B-MLX-6bit 🤖 Qwen3.6-27B-MLX-5bit 🤖 Qwen3.5-122B-A10B-GGUF 🤖 glm-4-9b-chat-IMat-GGUF 🤖 CodeLlama-7b-hf 🤖 Qwen2.5-1.5B-Instruct-AWQ 🤖 Qwen1.5-MoE-A2.7B 🤖 tiny-random-Gemma2ForCausalLM 🤖 Qwythos-9B-Claude-Mythos-5-1M-GGUF 🤖 gemma-4-31B-it-GGUF 🤖 gemma-4-26B-A4B-it-QAT-MLX-4bit 🤖 gemma-4-12B-coder-fable5-composer2.5-v1-GGUF 🤖 gemma-4-E4B-it-unsloth-bnb-4bit 🤖 MiniMax-M2.5 🤖 small-Qwen3ForCausalLM 🤖 Qwen3.5-35B-A3B-GPTQ-Int4 🤖 gemma-4-12b-it-GGUF 🤖 Ornith-1.5-35B-A3B-NVFP4 🤖 dots.mocr 🤖 Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF 🤖 Qwen3-0.6B-FP8 🤖 Parable-Qwen3-4B-Claude-Fable-5-GGUF 🤖 llava-v1.6-mistral-7b-hf 🤖 Ornith-1.0-35B-NVFP4 🤖 DeepSeek-V4-Flash-0731-NVFP4 🤖 Qwen3-30B-A3B-abliterated 🤖 Qwen3.5-122B-A10B-GPTQ-Int4 🤖 Qwen3-Coder-Next 🤖 blip2-opt-2.7b 🤖 Qwopus3.6-35B-A3B-Coder-MTP-GGUF 🤖 Mistral-7B-Instruct-v0.3-AWQ 🤖 gemma-3-27b-it 🤖 maple-preview-GGUF 🤖 Qwen2.5-72B-Instruct 🤖 Qwen3-4B-GGUF 🤖 Llama-3.2-1B-Instruct-FP8-dynamic 🤖 NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 🤖 gpt2-medium 🤖 Qwen3-VL-8B-Instruct-AWQ-4bit 🤖 gemma-4-31B-it-qat-q4_0-gguf 🤖 Qwen2.5-3B-Instruct-GGUF 🤖 Parable-Qwen3-8B-Claude-Fable-5-GGUF 🤖 Qwen3.5-4B-Base 🤖 Qwen3.5-27B-GGUF 🤖 pythia-14m 🤖 Qwen3-8B-Base 🤖 Qwen-AgentWorld-35B-A3B-GGUF 🤖 Ornith-1.0-397B-FP8 🤖 NVIDIA-Nemotron-Nano-9B-v2 🤖 Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 🤖 NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 🤖 Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP 🤖 Infinity-Parser2-Pro 🤖 Qwen2-7B-Instruct 🤖 saiga_llama3_8b 🤖 Laguna-S-2.1-NVFP4 🤖 Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive 🤖 Qwen3-VL-30B-A3B-Instruct 🤖 Qwen3.5-9B-Base 🤖 gemma-4-E2B-it-NVFP4 🤖 Hermes-3-Llama-3.1-8B 🤖 Qwen3.6-35B-A3B-NVFP4-Fast 🤖 Qwen3.6-35B-A3B-MLX-4bit 🤖 LightOnOCR-2-1B 🤖 GLM-5.2-GGUF 🤖 Qwen3-Coder-480B-A35B-Instruct-FP8 🤖 Qwen3-30B-A3B-GGUF 🤖 LFM2.5-1.2B-Instruct 🤖 Qwen2.5-VL-3B-Instruct-AWQ 🤖 Qwen3-30B-A3B-GPTQ-Int4 🤖 Qwen2.5-72B-Instruct-AWQ 🤖 Qwen3.6-27B-Uncensored-HauhauCS-Balanced 🤖 Tencent: Hy4 preview tencent 🤖 Ling 3.0 Flash Fin (free) inclusionai 🤖 Qwen: Qwen3.8 Flash qwen 🤖 Z.ai: GLM 5.3 Flash z-ai 🤖 Z.ai: GLM 5.3 Flash (batch) z-ai 🤖 Meta: Muse Spark 1.2 Contributor meta 🤖 DeepSeek: DeepSeek V4 Flash Vision Exp deepseek 🤖 Tencent: Hy-MT2-1.8B tencent 🤖 Tencent: Hy-MT2-30B-A3B tencent 🤖 Z.ai: GLM Latest ~z-ai 🤖 Tencent: Hy-MT2-7B tencent 🤖 Z.ai: GLM 5.3 z-ai 🤖 Qwen: Qwen3.8 27B qwen 🤖 Dots Studio: Dots3-Note Preview (free) dots-studio 🤖 Google: Gemini 3.7 Flash google 🤖 Google: Gemini 3.7 Flash (batch) google 🤖 ByteDance Seed: Seed 2.1 Turbo bytedance-seed 🤖 Qwen: Qwen3.8 2.4T A95B qwen 🤖 Qwen: Qwen3.8 2.4T A95B (batch) qwen 🤖 ByteDance Seed: Seed-2.0-Code bytedance-seed 🤖 DeepSeek: DeepSeek V4 Pro 0813 deepseek 🤖 DeepSeek: DeepSeek V4 Pro 0813 (batch) deepseek 🤖 SpaceXAI: Grok 4.6 x-ai 🤖 LiquidAI: LFM2.5-2.6B (free) liquid 🤖 NVIDIA: Nemotron 3.5 Lightning nvidia 🤖 NVIDIA: Nemotron 3.5 Lightning (free) nvidia 🤖 Sakana: Sakana Namazu sakana 🤖 Upstage: Solar Pro 4 upstage 🤖 Meta: Muse Glimmer 30B meta 🤖 Meta: Muse Glimmer 30B (batch) meta 🤖 Meta: Muse Spark 1.2 meta 🤖 Qwen: Qwen3.8 Max qwen 🤖 DeepSeek V4 Flash Latest ~deepseek 🤖 DeepSeek: DeepSeek V4 Flash 0731 deepseek 🤖 DeepSeek: DeepSeek V4 Flash 0731 (batch) deepseek 🤖 Thinking Machines: Inkling Small thinkingmachines 🤖 Thinking Machines: Inkling Small (batch) thinkingmachines 🤖 Thinking Machines: Inkling Small (free) thinkingmachines 🤖 Qwen: Qwen3.7 Flash qwen 🤖 Claude Opus 5 (Fast) anthropic 🤖 Claude Opus 5 anthropic 🤖 Claude Opus 5 (batch) anthropic 🤖 Ling-3.0-flash inclusionai 🤖 Poolside: Laguna S 2.1 poolside 🤖 Poolside: Laguna S 2.1 (free) poolside 🤖 Google: Gemini 3.6 Flash google 🤖 Google: Gemini 3.6 Flash (batch) google 🤖 Google: Gemini 3.5 Flash Lite google 🤖 Google: Gemini 3.5 Flash Lite (batch) google 🤖 Meituan: LongCat 2.0 meituan 🤖 Thinking Machines: Inkling thinkingmachines 🤖 Thinking Machines: Inkling (batch) thinkingmachines 🤖 Thinking Machines: Inkling (free) thinkingmachines 🤖 Auto Router (Beta) openrouter 🤖 MoonshotAI: Kimi K3 moonshotai 🤖 MoonshotAI: Kimi K3 (batch) moonshotai 🤖 Meta: Muse Spark 1.1 meta 🤖 Kwaipilot: KAT-Coder-Pro V2.5 kwaipilot 🤖 OpenAI: GPT-5.6 Luna Pro openai 🤖 OpenAI: GPT-5.6 Luna openai 🤖 OpenAI: GPT-5.6 Terra Pro openai 🤖 OpenAI: GPT-5.6 Terra openai 🤖 OpenAI: GPT-5.6 Sol Pro openai 🤖 OpenAI: GPT-5.6 Sol openai 🤖 SpaceXAI: Grok 4.5 x-ai 🤖 xAI: Grok Latest ~x-ai 🤖 AionLabs: Aion-3.0-Mini aion-labs 🤖 AionLabs: Aion-3.0 aion-labs 🤖 Tencent: Hy3 tencent 🤖 Poolside: Laguna XS 2.1 poolside 🤖 Poolside: Laguna XS 2.1 (free) poolside 🤖 Anthropic: Claude Sonnet 5 anthropic 🤖 Anthropic: Claude Sonnet 5 (batch) anthropic 🤖 Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) google 🤖 Nex AGI: Nex-N2-Mini nex-agi 🤖 Sakana: Fugu Ultra sakana 🤖 Google: Nano Banana 2 (Gemini 3.1 Flash Image) google 🤖 Google: Nano Banana Pro (Gemini 3 Pro Image) google 🤖 Cohere: North Mini Code (free) cohere 🤖 Z.ai: GLM 5.2 z-ai 🤖 Z.ai: GLM 5.2 (free) z-ai 🤖 OpenRouter: Fusion openrouter 🤖 MoonshotAI: Kimi K2.7 Code moonshotai 🤖 Anthropic: Claude Fable Latest ~anthropic 🤖 Anthropic: Claude Fable 5 anthropic 🤖 Anthropic: Claude Fable 5 (batch) anthropic 🤖 Nex AGI: Nex-N2-Pro nex-agi 🤖 NVIDIA: Nemotron 3.5 Content Safety (free) nvidia 🤖 NVIDIA: Nemotron 3 Ultra nvidia 🤖 NVIDIA: Nemotron 3 Ultra (batch) nvidia 🤖 NVIDIA: Nemotron 3 Ultra (free) nvidia 🤖 Qwen: Qwen3.7 Plus qwen 🤖 MiniMax: MiniMax M3 minimax 🤖 MiniMax: MiniMax M3 (batch) minimax 🤖 MiniMax: MiniMax M3 (free) minimax 🤖 StepFun: Step 3.7 Flash stepfun 🤖 Anthropic: Claude Opus 4.8 (Fast) anthropic 🤖 Anthropic: Claude Opus 4.8 anthropic 🤖 Anthropic: Claude Opus 4.8 (batch) anthropic 🤖 Qwen: Qwen3.7 Max qwen 🤖 SpaceXAI: Grok Build 0.1 x-ai 🤖 Google: Gemini 3.5 Flash google 🤖 Google: Gemini 3.5 Flash (batch) google 🤖 Anthropic: Claude Opus 4.7 (Fast) anthropic 🤖 Perceptron: Perceptron Mk1 perceptron 🤖 Google: Gemini 3.1 Flash Lite google 🤖 Google: Gemini 3.1 Flash Lite (batch) google 🤖 OpenAI: GPT Chat Latest openai 🤖 SpaceXAI: Grok 4.3 x-ai 🤖 IBM: Granite 4.1 8B ibm-granite 🤖 Mistral: Mistral Medium 3.5 mistralai 🤖 Mistral: Mistral Medium 3.5 (batch) mistralai 🤖 NVIDIA: Nemotron 3 Nano Omni (free) nvidia 🤖 Anthropic Claude Haiku Latest ~anthropic 🤖 OpenAI GPT Mini Latest ~openai 🤖 Google Gemini Pro Latest ~google 🤖 MoonshotAI Kimi Latest ~moonshotai 🤖 Google Gemini Flash Latest ~google 🤖 Anthropic Claude Sonnet Latest ~anthropic 🤖 OpenAI GPT Latest ~openai 🤖 Qwen: Qwen3.5 Plus 2026-04-20 qwen 🤖 Qwen: Qwen3.6 Flash qwen 🤖 Qwen: Qwen3.6 35B A3B qwen 🤖 Qwen: Qwen3.6 Max Preview qwen 🤖 Qwen: Qwen3.6 27B qwen 🤖 OpenAI: GPT-5.5 Pro openai 🤖 OpenAI: GPT-5.5 openai 🤖 DeepSeek: DeepSeek V4 Pro 0423 deepseek 🤖 DeepSeek: DeepSeek V4 Flash 0423 deepseek 🤖 Tencent: Hy3 preview tencent 🤖 Xiaomi: MiMo-V2.5-Pro xiaomi 🤖 Xiaomi: MiMo-V2.5 xiaomi 🤖 OpenAI: GPT-5.4 Image 2 openai 🤖 Anthropic: Claude Opus Latest ~anthropic 🤖 Pareto Code Router openrouter 🤖 MoonshotAI: Kimi K2.6 moonshotai 🤖 Anthropic: Claude Opus 4.7 anthropic 🤖 Anthropic: Claude Opus 4.7 (batch) anthropic 🤖 Z.ai: GLM 5.1 z-ai 🤖 Google: Gemma 4 26B A4B google 🤖 Google: Gemma 4 26B A4B (free) google 🤖 Google: Gemma 4 31B google 🤖 Google: Gemma 4 31B (batch) google 🤖 Google: Gemma 4 31B (free) google 🤖 Qwen: Qwen3.6 Plus qwen 🤖 Z.ai: GLM 5V Turbo z-ai 🤖 Arcee AI: Trinity Large Thinking arcee-ai 🤖 SpaceXAI: Grok 4.20 Multi-Agent x-ai 🤖 SpaceXAI: Grok 4.20 x-ai 🤖 Google: Lyria 3 Pro Preview google 🤖 Google: Lyria 3 Clip Preview google 🤖 Kwaipilot: KAT-Coder-Pro V2 kwaipilot 🤖 Reka Edge rekaai 🤖 MiniMax: MiniMax M2.7 minimax 🤖 MiniMax: MiniMax M2.7 (free) minimax 🤖 OpenAI: GPT-5.4 Nano openai 🤖 OpenAI: GPT-5.4 Mini openai 🤖 Mistral: Mistral Small 4 mistralai 🤖 Mistral: Mistral Small 4 (batch) mistralai 🤖 Z.ai: GLM 5 Turbo z-ai 🤖 NVIDIA: Nemotron 3 Super nvidia 🤖 NVIDIA: Nemotron 3 Super (free) nvidia 🤖 ByteDance Seed: Seed-2.0-Lite bytedance-seed 🤖 Qwen: Qwen3.5-9B qwen 🤖 Qwen: Qwen3.5-9B (batch) qwen 🤖 OpenAI: GPT-5.4 Pro openai 🤖 OpenAI: GPT-5.4 openai 🤖 Inception: Mercury 2 inception 🤖 Google: Gemini 3.1 Flash Lite Preview google 🤖 ByteDance Seed: Seed-2.0-Mini bytedance-seed 🤖 Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) google 🤖 Qwen: Qwen3.5-35B-A3B qwen 🤖 Qwen: Qwen3.5-27B qwen 🤖 Qwen: Qwen3.5-122B-A10B qwen 🤖 Qwen: Qwen3.5-Flash qwen 🤖 Google: Gemini 3.1 Pro Preview Custom Tools google 🤖 OpenAI: GPT-5.3-Codex openai 🤖 AionLabs: Aion-2.0 aion-labs 🤖 Google: Gemini 3.1 Pro Preview google 🤖 Google: Gemini 3.1 Pro Preview (batch) google 🤖 Anthropic: Claude Sonnet 4.6 anthropic 🤖 Anthropic: Claude Sonnet 4.6 (batch) anthropic 🤖 Qwen: Qwen3.5 Plus 2026-02-15 qwen 🤖 Qwen: Qwen3.5 397B A17B qwen 🤖 MiniMax: MiniMax M2.5 minimax 🤖 Z.ai: GLM 5 z-ai 🤖 Qwen: Qwen3 Max Thinking qwen 🤖 Anthropic: Claude Opus 4.6 anthropic 🤖 Anthropic: Claude Opus 4.6 (batch) anthropic 🤖 Qwen: Qwen3 Coder Next qwen 🤖 Free Models Router openrouter 🤖 StepFun: Step 3.5 Flash stepfun 🤖 MoonshotAI: Kimi K2.5 moonshotai 🤖 Upstage: Solar Pro 3 upstage 🤖 MiniMax: MiniMax M2-her minimax 🤖 Writer: Palmyra X5 writer 🤖 OpenAI: GPT Audio openai 🤖 OpenAI: GPT Audio Mini openai 🤖 Z.ai: GLM 4.7 Flash z-ai 🤖 OpenAI: GPT-5.2-Codex openai 🤖 ByteDance Seed: Seed 1.6 Flash bytedance-seed 🤖 ByteDance Seed: Seed 1.6 bytedance-seed 🤖 MiniMax: MiniMax M2.1 minimax 🤖 Z.ai: GLM 4.7 z-ai 🤖 Google: Gemini 3 Flash Preview google 🤖 Google: Gemini 3 Flash Preview (batch) google 🤖 NVIDIA: Nemotron 3 Nano 30B A3B nvidia 🤖 OpenAI: GPT-5.2 Chat openai 🤖 OpenAI: GPT-5.2 Pro openai 🤖 OpenAI: GPT-5.2 openai 🤖 Mistral: Devstral 2 2512 mistralai 🤖 Relace: Relace Search relace 🤖 Z.ai: GLM 4.6V z-ai 🤖 Body Builder (beta) openrouter 🤖 OpenAI: GPT-5.1-Codex-Max openai 🤖 Amazon: Nova 2 Lite amazon 🤖 Mistral: Ministral 3 14B 2512 mistralai 🤖 Mistral: Ministral 3 8B 2512 mistralai 🤖 Mistral: Ministral 3 8B 2512 (batch) mistralai 🤖 Mistral: Ministral 3 3B 2512 mistralai 🤖 Mistral: Mistral Large 3 2512 mistralai 🤖 Mistral: Mistral Large 3 2512 (batch) mistralai 🤖 DeepSeek: DeepSeek V3.2 deepseek 🤖 Anthropic: Claude Opus 4.5 anthropic 🤖 Anthropic: Claude Opus 4.5 (batch) anthropic 🤖 Google: Nano Banana Pro (Gemini 3 Pro Image Preview) google 🤖 OpenAI: GPT-5.1 openai 🤖 OpenAI: GPT-5.1-Codex openai 🤖 OpenAI: GPT-5.1-Codex-Mini openai 🤖 MoonshotAI: Kimi K2 Thinking moonshotai 🤖 Amazon: Nova Premier 1.0 amazon 🤖 Perplexity: Sonar Pro Search perplexity 🤖 Mistral: Voxtral Small 24B 2507 mistralai 🤖 OpenAI: gpt-oss-safeguard-20b openai 🤖 MiniMax: MiniMax M2 minimax 🤖 Qwen: Qwen3 VL 32B Instruct qwen 🤖 IBM: Granite 4.0 Micro ibm-granite 🤖 OpenAI: GPT-5 Image Mini openai 🤖 Anthropic: Claude Haiku 4.5 anthropic 🤖 Anthropic: Claude Haiku 4.5 (batch) anthropic 🤖 Qwen: Qwen3 VL 8B Thinking qwen 🤖 Qwen: Qwen3 VL 8B Instruct qwen 🤖 OpenAI: GPT-5 Image openai 🤖 Google: Nano Banana (Gemini 2.5 Flash Image) google 🤖 Qwen: Qwen3 VL 30B A3B Thinking qwen 🤖 Qwen: Qwen3 VL 30B A3B Instruct qwen 🤖 OpenAI: GPT-5 Pro openai 🤖 Z.ai: GLM 4.6 z-ai 🤖 Anthropic: Claude Sonnet 4.5 anthropic 🤖 Anthropic: Claude Sonnet 4.5 (batch) anthropic 🤖 DeepSeek: DeepSeek V3.2 Exp deepseek 🤖 TheDrummer: Cydonia 24B V4.1 thedrummer 🤖 Relace: Relace Apply 3 relace 🤖 Qwen: Qwen3 VL 235B A22B Thinking qwen 🤖 Qwen: Qwen3 VL 235B A22B Instruct qwen 🤖 Qwen: Qwen3 Max qwen 🤖 Qwen: Qwen3 Coder Plus qwen 🤖 DeepSeek: DeepSeek V3.1 Terminus deepseek 🤖 Qwen: Qwen3 Coder Flash qwen 🤖 Qwen: Qwen3 Next 80B A3B Thinking qwen 🤖 Qwen: Qwen3 Next 80B A3B Instruct qwen 🤖 Qwen: Qwen Plus 0728 qwen 🤖 MoonshotAI: Kimi K2 0905 moonshotai 🤖 Qwen: Qwen3 30B A3B Thinking 2507 qwen 🤖 Nous: Hermes 4 70B nousresearch 🤖 Nous: Hermes 4 405B nousresearch 🤖 DeepSeek: DeepSeek V3.1 deepseek 🤖 Mistral: Mistral Medium 3.1 mistralai 🤖 Mistral: Mistral Medium 3.1 (batch) mistralai 🤖 Z.ai: GLM 4.5V z-ai 🤖 OpenAI: GPT-5 openai 🤖 OpenAI: GPT-5 Mini openai 🤖 OpenAI: GPT-5 Nano openai 🤖 OpenAI: gpt-oss-120b openai 🤖 OpenAI: gpt-oss-120b (batch) openai 🤖 OpenAI: gpt-oss-20b openai 🤖 OpenAI: gpt-oss-20b (batch) openai 🤖 Anthropic: Claude Opus 4.1 anthropic 🤖 Anthropic: Claude Opus 4.1 (batch) anthropic 🤖 Mistral: Codestral 2508 mistralai 🤖 Mistral: Codestral 2508 (batch) mistralai 🤖 Qwen: Qwen3 Coder 30B A3B Instruct qwen 🤖 Qwen: Qwen3 30B A3B Instruct 2507 qwen 🤖 Z.ai: GLM 4.5 z-ai 🤖 Z.ai: GLM 4.5 Air z-ai 🤖 Qwen: Qwen3 235B A22B Thinking 2507 qwen 🤖 Qwen: Qwen3 Coder 480B A35B qwen 🤖 ByteDance: UI-TARS 7B bytedance 🤖 Google: Gemini 2.5 Flash Lite google 🤖 Google: Gemini 2.5 Flash Lite (batch) google 🤖 Qwen: Qwen3 235B A22B Instruct 2507 qwen 🤖 MoonshotAI: Kimi K2 0711 moonshotai 🤖 Venice: Uncensored cognitivecomputations 🤖 Tencent: Hunyuan A13B Instruct tencent 🤖 Morph: Morph V3 Large morph 🤖 Morph: Morph V3 Fast morph 🤖 Baidu: ERNIE 4.5 VL 424B A47B baidu 🤖 Mistral: Mistral Small 3.2 24B mistralai 🤖 MiniMax: MiniMax M1 minimax 🤖 Google: Gemini 2.5 Flash google 🤖 Google: Gemini 2.5 Flash (batch) google 🤖 Google: Gemini 2.5 Pro google 🤖 Google: Gemini 2.5 Pro (batch) google 🤖 OpenAI: o3 Pro openai 🤖 Google: Gemini 2.5 Pro Preview 06-05 google 🤖 Anthropic: Claude Opus 4 anthropic 🤖 Anthropic: Claude Sonnet 4 anthropic 🤖 Mistral: Mistral Medium 3 mistralai 🤖 Google: Gemini 2.5 Pro Preview 05-06 google 🤖 Meta: Llama Guard 4 12B meta-llama 🤖 Qwen: Qwen3 30B A3B qwen 🤖 Qwen: Qwen3 8B qwen 🤖 Qwen: Qwen3 14B qwen 🤖 Qwen: Qwen3 32B qwen 🤖 Qwen: Qwen3 235B A22B qwen 🤖 OpenAI: o4 Mini High openai 🤖 OpenAI: o3 openai 🤖 OpenAI: o4 Mini openai 🤖 OpenAI: GPT-4.1 openai 🤖 OpenAI: GPT-4.1 Mini openai 🤖 OpenAI: GPT-4.1 Nano openai 🤖 Meta: Llama 4 Maverick meta-llama 🤖 Meta: Llama 4 Scout meta-llama 🤖 DeepSeek: DeepSeek V3 0324 deepseek 🤖 OpenAI: o1-pro openai 🤖 Mistral: Mistral Small 3.1 24B mistralai 🤖 Google: Gemma 3 4B google 🤖 Google: Gemma 3 12B google 🤖 Cohere: Command A cohere 🤖 Reka Flash 3 rekaai 🤖 Google: Gemma 3 27B google 🤖 TheDrummer: Skyfall 36B V2 thedrummer 🤖 Perplexity: Sonar Reasoning Pro perplexity 🤖 Perplexity: Sonar Pro perplexity 🤖 Perplexity: Sonar Deep Research perplexity 🤖 Mistral: Saba mistralai 🤖 OpenAI: o3 Mini High openai 🤖 AionLabs: Aion-RP 1.0 (8B) aion-labs 🤖 Qwen: Qwen2.5 VL 72B Instruct qwen 🤖 Qwen: Qwen-Plus qwen 🤖 OpenAI: o3 Mini openai 🤖 Mistral: Mistral Small 3 mistralai 🤖 Perplexity: Sonar perplexity 🤖 MiniMax: MiniMax-01 minimax 🤖 Microsoft: Phi 4 microsoft 🤖 DeepSeek: DeepSeek V3 deepseek 🤖 Sao10K: Llama 3.3 Euryale 70B sao10k 🤖 OpenAI: o1 openai 🤖 Cohere: Command R7B (12-2024) cohere 🤖 Meta: Llama 3.3 70B Instruct meta-llama 🤖 Amazon: Nova Lite 1.0 amazon 🤖 Amazon: Nova Micro 1.0 amazon 🤖 Amazon: Nova Pro 1.0 amazon 🤖 OpenAI: GPT-4o (2024-11-20) openai 🤖 Mistral Large 2407 mistralai 🤖 TheDrummer: UnslopNemo 12B thedrummer 🤖 Magnum v4 72B anthracite-org 🤖 Qwen: Qwen2.5 7B Instruct qwen 🤖 Meta: Llama 3.2 1B Instruct meta-llama 🤖 Meta: Llama 3.2 3B Instruct meta-llama 🤖 Cohere: Command R (08-2024) cohere 🤖 Sao10K: Llama 3.1 Euryale 70B v2.2 sao10k 🤖 Nous: Hermes 3 70B Instruct nousresearch 🤖 Nous: Hermes 3 405B Instruct nousresearch 🤖 Sao10K: Llama 3 8B Lunaris sao10k 🤖 OpenAI: GPT-4o (2024-08-06) openai 🤖 Meta: Llama 3.1 70B Instruct meta-llama 🤖 Meta: Llama 3.1 8B Instruct meta-llama 🤖 Mistral: Mistral Nemo mistralai 🤖 OpenAI: GPT-4o-mini openai 🤖 OpenAI: GPT-4o-mini (2024-07-18) openai 🤖 Google: Gemma 2 27B google 🤖 OpenAI: GPT-4o openai 🤖 OpenAI: GPT-4o (2024-05-13) openai 🤖 Mistral: Mixtral 8x22B Instruct mistralai 🤖 WizardLM-2 8x22B microsoft 🤖 OpenAI: GPT-4 Turbo openai 🤖 Anthropic: Claude 3 Haiku anthropic 🤖 Mistral Large mistralai 🤖 OpenAI: GPT-3.5 Turbo (older v0613) openai 🤖 OpenAI: GPT-4 Turbo Preview openai 🤖 Auto Router openrouter 🤖 OpenAI: GPT-3.5 Turbo Instruct openai 🤖 OpenAI: GPT-3.5 Turbo 16k openai 🤖 Mancer: Weaver (alpha) mancer 🤖 ReMM SLERP 13B undi95 🤖 MythoMax 13B gryphe 🤖 OpenAI: GPT-3.5 Turbo openai 🤖 OpenAI: GPT-4 openai

Select 2-5 models

Attribute	🤖 Qwen3.6-27B-FP8
Company
Release Date	2026-04-21
Parameters (B)	27
Architecture	Hybrid Gated DeltaNet-Attention Transformer with Vision Encoder
Context Window	262144
Input Modalities	text, image, video
Open Source	Yes
License	apache-2.0
Score	8.7
VRAM (GB)	28
Compute	Official FP8 weights (~25 GB) need roughly 28–32 GB VRAM for stable single-GPU inference; recommended setups include RTX 5090 (32 GB), H100, or dual 24 GB GPUs (e.g., 2× RTX 4090) with tensor parallelism. Best served via vLLM or SGLang with MTP speculative decoding on FP8-capable NVIDIA GPUs.
Benchmark: GSM8K	93.3
Benchmark: HumanEval	83.9
Benchmark: MMLU	86.2
Pricing (Input)	—
Pricing (Output)	—