Qwen3.8-27B-NVFP4-RTX5090
Runs on SparkInfer, SGLang and vLLM unmodified — configs for all three are below. Serving many users at once? See concurrency.
Params
27.0 B
Context
—
Downloads 30d
826 K
Likes
165
Download history
tracking started — chart appears after 7 days of snapshots (3 recorded)826 K downloads in the last 30 days
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 | u8 | 17.9 GB | 24.3 GB | ❌ Won’t fit |
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
- 27.0 B
- Tensor type
- U8
- Licence
- apache-2.0
- First seen on the Hub
- 2026-08-14
- Base model
- Qwen3.8-27B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-19
Compare with any image-text-to-text model