Downloads · 30 days
0
Qwen3.6-27B-MTP-exl3
turboderp/Qwen3.6-27B-MTP-exl3
Qwen3.6-27B-MTP-exl3 is a machine learning model from turboderp. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
These are the MTP tensors for Qwen3.6-27B, quantized at 4 bpw.
Access
Public
Updated Jun 8, 2026
Repo size
213 MB
Likes
12
Public
Repo makeup
Click a slice to open those files.
.safetensors213 MB · 100%
At a glance
- Access
- Public
- Created
- Jun 8, 2026
- Updated
- Jun 8, 2026
- SHA
- 5edc96ec
Model card
From the Hugging Face model README
These are the MTP tensors for Qwen3.6-27B, quantized at 4 bpw.
Qwen3.5/3.6 checkpoints quantized with exllamav3 v0.0.41+ will automatically contain MTP layers. For quantized checkpoints from earlier versions, place this file in the model directory to enable MTP drafting.
Quick benchmark (RTX 6000 Pro, 4.00 bpw target model):
| Category | Baseline | MTP (greedy) |
|---|---|---|
| Agentic, code | 63.88 t/s | 180.51 t/s, 2.83x |
| Agentic, curl | 61.42 t/s | 154.40 t/s, 2.51x |
| Coding | 68.17 t/s | 187.97 t/s, 2.76x |
| Creative | 68.29 t/s | 138.22 t/s, 2.02x |
| Creative (reasoning) | 68.01 t/s | 135.00 t/s, 1.98x |
| Translation | 66.88 t/s | 139.41 t/s, 2.08x |
| Translation (reasoning) | 66.79 t/s | 162.90 t/s, 2.44x |
| Trivial repetition | 68.87 t/s | 237.59 t/s, 3.45x |
- Created
- Jun 8, 2026
- Updated
- Jun 8, 2026