Downloads · 30 days
53
7% of all-time downloads
robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp_visualsupport
hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp_visualsupport is a image-text-to-text model from robinshao. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repo contains the local serving package for HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive using a robinshao-style MXFP4MOE main GGUF, a separate MTP draft GGUF for speculative decoding, and a separate m…
Downloads · 30 days
53
7% of all-time downloads
All-time downloads
711
Public
Repo size
21.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf21.2 GB · 100%
From the Hugging Face model README
This repo contains the local serving package for HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive using a robinshao-style MXFP4_MOE main GGUF, a separate MTP draft GGUF for speculative decoding, and a separate multimodal mmproj GGUF for image input support in patched llama.cpp.
hauhau_qwen36_35b_a3b_mxfp4_robinstyle.gguf: main text model in robinshao-style MXFP4 layouthauhau_qwen36_35b_a3b_mxfp4_mtp.gguf: MTP draft GGUF used with --spec-type draft-mtpmmproj-Hauhau_Qwen36_35B_A3B_Fp16-Q8_0.gguf: multimodal projector / vision encoder GGUFllama.cpp.src-patched.zip: patched local llama.cpp source snapshot used for conversion and servingbuild_result.json: build and validation summarymtp-benchmark.json: short local speed comparison for the text+MTP serving pairkhoi11/Qwen3.6-35B-A3B-Uncensored-HauhauCS-FP16HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressivemmproj GGUF from the original multimodal FP16 checkpointmmproj fileValidated locally on Windows with patched llama.cpp using speculative decoding and multimodal input:
llama-server -m hauhau_qwen36_35b_a3b_mxfp4_robinstyle.gguf --mmproj mmproj-Hauhau_Qwen36_35B_A3B_Fp16-Q8_0.gguf --spec-type draft-mtp --spec-draft-model hauhau_qwen36_35b_a3b_mxfp4_mtp.gguf --spec-draft-device CUDA0 --spec-draft-ngl all --jinja --device CUDA0 --gpu-layers all --ctx-size 8192 --batch-size 512 --ubatch-size 128 --flash-attn on --cache-type-k f16 --cache-type-v f16 --cache-ram 0
Local validation confirmed:
draft-mtpmmproj loads successfully/v1/chat/completions accepts image inputmmproj file.--mmproj, the package behaves like the earlier text-only MTP release.262144, but local no-offload limits still depend on VRAM, KV cache settings, and whether the draft model is loaded.