Downloads · 30 days
459
1% of all-time downloads
AesSedai/Qwen3.5-35B-A3B-GGUF
Qwen3.5-35B-A3B-GGUF is a machine learning model from AesSedai. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- 5/18/2026: I've uploaded new quants that include the MTP Tensors (@ Q80). - 3/10/2026: I've uploaded new quants using the new fused Up + Gate conversion, this offers up to a +10% boost in prompt processing speed fro…
Downloads · 30 days
459
1% of all-time downloads
All-time downloads
55.9K
Public
Repo size
87.5 GB
Likes
85
Public
Click a slice to open those files.
.gguf87.5 GB · 100%
From the Hugging Face model README
This repo contains specialized MoE-quants for Qwen3.5-35B-A3B. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization. To that end, the quantization type default is kept in high quality and the FFN UP + FFN GATE tensors are quanted down along with the FFN DOWN tensors.
| Quant | Size | Mixture | PPL | 1-(Mean PPL(Q)/PPL(base)) | KLD |
|---|---|---|---|---|---|
| Q8_0 | 35.19 GiB (8.51 BPW) | Q8_0 | 6.535248 ± 0.041570 | +0.0252% | 0.004522 ± 0.000057 |
| Q5_K_M | 25.28 GiB (6.12 BPW) | Q8_0 / Q5_K / Q5_K / Q6_K | 6.534171 ± 0.041557 | +0.0087% | 0.006066 ± 0.000056 |
| Q4_K_M | 21.45 GiB (5.19 BPW) | Q8_0 / Q4_K / Q4_K / Q5_K | 6.560168 ± 0.041799 | +0.4066% | 0.009884 ± 0.000075 |
| IQ4_XS | 17.23 GiB (4.17 BPW) | Q8_0 / IQ3_S / IQ3_S / IQ4_XS | 6.635447 ± 0.042320 | +1.5588% | 0.023868 ± 0.000204 |
| IQ3_S | 13.48 GiB (3.26 BPW) | Q6_K / IQ2_S / IQ2_S / IQ3_S | 6.920209 ± 0.044626 | +5.9172% | 0.061977 ± 0.000394 |
