jamiefutch/Qwen3.5-35B-A3B-MXFP4_MOE-GGUF overview
These are quantizations of the model Qwen3.5 35B A3B https://huggingface.co/unsloth/Qwen3.5 35B A3B Download the latest llama.cpp https://github.com/ggml org/l…
Runs locally from ~861.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | jamiefutch/Qwen3.5-35B-A3B-MXFP4_MOE-GGUF |
|---|---|
| Author | jamiefutch |
| Pipeline | image-text-to-text |
| License | — |
| Base model | Qwen/Qwen3.5-35B-A3B |
| Last modified | 2026-07-06T10:19:25.000Z |
Model README
---
pipeline_tag: image-text-to-text
base_model:
- Qwen/Qwen3.5-35B-A3B
---
These are quantizations of the model Qwen3.5-35B-A3B
- Download the latest llama.cpp to use these quantizations.
- For the
mmprojfile, the F32 version is recommended for best results.
The mmproj files are the same from unsloth.
Read the guide from unsloth in order to set up the model's recommended settings:
Qwen3.5 - How to Run Locally Guide
The mainline standard is to use MXFP4 for the MoE tensors, and Q8 for the rest.
So I created 2 new variants, where the other tensors are either BF16 or FP16 instead of Q8.
The order of preference is BF16, then F16.
On some architectures BF16 will be slower, but its the highest quality, essentialy its the original tensors from the model copied over unquantized.
As of 2026-03-03 the chat template has been updated, and is using the fixed version from unsloth.
If you don't want to download the model again, you can just update the chat template.
Run jamiefutch/Qwen3.5-35B-A3B-MXFP4_MOE-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models