Downloads · 30 days
789
5% of all-time downloads
noctrex/Qwen3.6-35B-A3B-MXFP4_MOE-GGUF
Qwen3.6-35B-A3B-MXFP4_MOE-GGUF is a image-text-to-text model from noctrex. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product.
These are MXFP4 quantizations of the model Qwen3.6-35B-A3B
Downloads · 30 days
789
5% of all-time downloads
All-time downloads
17.4K
Public
Repo size
68 GB
Likes
12
Public
Click a slice to open those files.
.gguf68 GB · 100%
From the Hugging Face model README
These are MXFP4 quantizations of the model Qwen3.6-35B-A3B
mmproj file, it is recommended to use the F32 version for the best visual processing results. F32 > BF16 > F16All variants use MXFP4 for the MoE (Mixture of Experts) weights to keep the model efficient. The difference lies in how the remaining tensors are handled:
| Variant | Quality | Performance | Size | Recommendation |
|---|---|---|---|---|
| BF16 | ⭐⭐⭐ | Variable* | 20.55GiB | Best for maximum accuracy; original unquantized weights. |
| F16 | ⭐⭐ | Fast | 20.55GiB | Great alternative if BF16 is slow on your hardware. |
| Q8 | ⭐ | Fastest | 18.88GiB | Balanced performance and memory usage. |
**Note: On some older architectures, BF16 may be slower than F16. Check that your GPU supports native BF16 *
Read the guide from unsloth in order to set up the model's recommended settings:
Qwen3.6 - How to Run Locally Guide