LLM Models · Open Source
Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.
Qwen2.5 Bakeneko 32B Instruct AWQ (rinna/qwen2.5-bakeneko-32b-instruct-awq)
QwQ Bakeneko 32B GPTQ int4 (rinna/qwq-bakeneko-32b-gptq-int4)
Qwen2.5 Bakeneko 32B Instruct GPTQ int4 (rinna/qwen2.5-bakeneko-32b-instruct-gptq-int4)
Qwen2.5 Bakeneko 32B Instruct V2 GPTQ int8 (rinna/qwen2.5-bakeneko-32b-instruct-v2-gptq-int8)
Qwen2.5 Bakeneko 32B Instruct GPTQ int8 (rinna/qwen2.5-bakeneko-32b-instruct-gptq-int8)
Qwen2.5 Bakeneko 32B Instruct V2 GPTQ int4 (rinna/qwen2.5-bakeneko-32b-instruct-v2-gptq-int4)
QwQ Bakeneko 32B AWQ (rinna/qwq-bakeneko-32b-awq)
Qwen2.5 Bakeneko 32B Instruct V2 AWQ (rinna/qwen2.5-bakeneko-32b-instruct-v2-awq)
QwQ Bakeneko 32B GPTQ int8 (rinna/qwq-bakeneko-32b-gptq-int8)
Model Introduction We introduce LongCat-2.0, a large-scale MoE language model with 1.6 trillion total parameters and ~48 billion activated per token — a substantial step up from previous LongCat models, accompanied by several architectural improvements.
Model Introduction We introduce LongCat-2.0, a large-scale MoE language model with 1.6 trillion total parameters and ~48 billion activated per token — a substantial step up from previous LongCat models, accompanied by several architectural improvements.
Model Introduction We introduce LongCat-2.0, a large-scale MoE language model with 1.6 trillion total parameters and ~48 billion activated per token — a substantial step up from previous LongCat models, accompanied by several architectural improvements.