Downloads · 30 days
27
7% of all-time downloads
robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf
hauhau_qwen36_35b_a3b_mxfp4_gguf is a text generation model from robinshao. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
This repo contains a local MXFP4MOE GGUF conversion of HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive, prepared with a patched local llama.cpp toolchain.
Downloads · 30 days
27
7% of all-time downloads
All-time downloads
393
Public
Repo size
19.1 GB
Likes
0
Public
Click a slice to open those files.
.gguf19 GB · 100%
From the Hugging Face model README
This repo contains a local MXFP4_MOE GGUF conversion of HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive, prepared with a patched local llama.cpp toolchain.
hauhau_qwen36_35b_a3b_mxfp4_gguf.gguf: text-only GGUF export in robinshao-style MXFP4 layoutllama.cpp.src-patched.zip: patched local llama.cpp source snapshot used for conversion and servingbuild_result.json: conversion and quantization summaryapi-benchmark.json: basic local API benchmark outputkhoi11/Qwen3.6-35B-A3B-Uncensored-HauhauCS-FP16HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressiveconvert_hf_to_gguf.py --outtype f16 --no-mtpllama-quantize using MXFP4_MOE --pure --output-tensor-type q8_0 --token-embedding-type q8_0{
"tensor_count": 733,
"type_counts": {
"Q8_0": 2,
"F32": 301,
"MXFP4": 430
},
"output_bytes": 19041835392
}
This file was validated locally with patched llama.cpp on Windows using:
llama-server -m hauhau_qwen36_35b_a3b_mxfp4_gguf.gguf \
--jinja \
--device CUDA0 \
--gpu-layers all \
--ctx-size 110592 \
--batch-size 768 \
--ubatch-size 128 \
--flash-attn on
Local API benchmark on an RTX 4000 Ada at ctx-size=110592 observed roughly 103-105 tok/s decode speed for short requests.
262144, but the local validation run used 110592.