Modelpublic

michaelw9999/Qwen3.6-35B-A3B-NVFP4-MTP-GGUF

sourceHugging Faceupdated 4mo agoView on Hugging Face

12likes366kdownloads

Model Card

Qwen3.6-35B-A3B-NVFP4-MTP-GGUF

This repo contains two experimental NVFP4 GGUF quantizations of Qwen3.6-35B-A3B for llama.cpp.<BR> This was quantized using my experimental <A HREF="https://github.com/michaelw9999/advanced-gguf-quantizer/">advanced-gguf-quantizer</A> tool.<BR> Both models were imatrix calibrated for the first time using a new custom dataset that I am evaluating.

This repository contains two NVFP4 variants:

Variant	File	Best for	Notes
TURBO	`Qwen3.6-35B-A3B-NVFP4-MTP-TURBO.gguf`	Max speed	More NVFP4. Lower quality metrics.
HQ	`Qwen3.6-35B-A3B-NVFP4-MTP-HQ.gguf`	Better quality	More tensors promoted. Slightly slower.

Quality & Speed Results

All PPL/KLD results were measured against the same BF16 wikitest KLD base, and then compared to the official NVFP4 release by NVIDIA.

Metric	TURBO	HQ	NVIDIA-NVFP4
Size	18.56 GiB	18.64 GiB	22.20 GiB
Mean PPL(Q)	6.987392	6.897796	7.014030
Mean PPL(Q)-PPL(base)	0.268551	0.178955	—
Mean PPL ratio	1.039970	1.026635	1.043935
Mean ln(PPL ratio)	0.039192	0.026286	—
Mean KLD	0.063228	0.050759	0.066331
99.9% KLD	1.924147	1.565143	1.560988
99.0% KLD	0.598519	0.488387	0.495896
95.0% KLD	0.221030	0.178889	0.207580
Max KLD	11.946571	10.093911	6.972712
Same top p	89.023%	90.255%	87.608%
Top flip weight	0.012068	0.009575	—
pp512	11593.57 t/s	10936.20 t/s	10426.32 t/s
tg128	271.21 t/s	270.49 t/s	221.86 t/s

Evaluation Results

Further evaluation tests are underway to identify real world performance differences between TURBO and HQ.

Benchmark	Samples	TURBO	HQ	NVIDIA-NVFP4
GSM8K	103	98%	98%	97%
HellaSwag	100	89%	89%	89%
HumanEval	164	96.34%	95.12%	95.12%