---

license: other

base_model:

• Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash
• unsloth/Qwen3.5-9B

private: true

---

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.