전체 검색

AI 모델 84759

• Qwen3-4B-Instruct-2507-GPTQ-Int8↗

  JunHowie

  Compared to earlier quantized versions, the new quantized model demonstrates better tokens/s efficiency. This improvement comes from setting desc_act=False in the quantization configuration. We introduce the updated version of the **Qwen3-4B non-thinking mode**, named **Qwen3-4B-Instruct-2507**, featuring the following key enhancements: **Qwen3-4B-Instruct-2507** has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 4.0B - Number of Paramaters (Non-Embedding): 3.6B - Number of Layers: 36 - Number of Attention Heads (GQA): 32 for Q and 8 for KV - Context Length: **262,144 natively**.

• Gemma-3-27b-it-Uncensored-HERETIC-Gemini-Deep-Reasoning-Q4_K_M-GGUF↗

  kainah

• kling-image-expend↗

  快手 · 可灵

  扩图

• turnsense↗

  latishab

• noobai-XL-Vpred-0.6↗

  Laxhar

• LTX-Video-0.9.7-distilled↗

  Lightricks

• Tucan-2.6B-v1.0-GGUF↗

  llm-bg

• Ru-Small-Instruct↗

  longtimedevs

• GLM-4.5-Air-3bit↗

  mlx-community

• nemotron-3.5-asr-streaming-0.6b↗

  mlx-community