Qwen3.8-27B-4bit
--- libraryname: mlx license: apache-2.0 pipelinetag: image-text-to-text basemodel: Qwen/Qwen3.8-27B tags: - mlx ---
Params
27.4 B
Context
—
Downloads 30d
880 K
Likes
223
Download history
daily snapshots · 11 days886 K800 K
Oct 14Oct 17Oct 21Oct 24
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | u32 | 16.1 GB | 22.3 GB | ⚠️ Tight — reduce context |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- Qwen3_5ForConditionalGeneration
- Parameters
- 27.4 B
- Tensor type
- U32
- Licence
- apache-2.0
- First seen on the Hub
- 2026-08-14
- Base model
- Qwen3.8-27B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-14
Compare with any image-text-to-text model