Jackrong/Qwen3.5 9B DeepSeek V4 Flash MTP GGUF Source model: Jackrong/Qwen3.5 9B DeepSeek V4 Flash MTP source fallback: unsloth/Qwen3.5 9B Uploaded GGUF variants: Qwen3.5 9B DeepSeek V4 Flash MTP Q2 K.gguf Qwen3.5 9B DeepSeek V4 Flash MTP Q3 K S.gguf Qwen3.5 9B DeepSeek V4 Flash MTP Q3 K M.gguf Qwen3.5 9B DeepSeek V4 Flash MTP Q3 K L.gguf Qwen3.5 9B DeepSeek V4 Flash MTP IQ4 XS.gguf Qwen3.5 9B DeepSeek V4 Flash MTP Q4 K S.gguf Qwen3.5 9B DeepSeek V4 Flash MTP Q4 K M.gguf Qwen3.5 9B DeepSeek V4 Flash MTP Q5 K S.gguf Qwen3.5 9B DeepSeek V4 Flash MTP Q5 K M.gguf Qwen3.5 9B DeepSeek V4 Flash MTP Q6 K.gguf Qwen3.5 9B DeepSeek V4 Flash MTP Q8 0.gguf Qwen3.5 9B DeepSeek V4 Flash MTP BF16.gguf The conversion pipeline first verifies whether the source HF model already contains MTP tensors. If not, it extracts the MTP tensors from the matching unsloth base model and injects them into the safetensors index before GGUF conversion.
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy