Qwen3.8 27B
Qwen3.8 27B
Architecture & parameters
| Parameters (total) | 27.8B |
|---|---|
| Parameters (active) | 27.8B |
| Architecture | qwen3_5 |
| Layers | 64 |
| KV heads | 4 |
| Native context | 262144 |
Artifacts
| File | Publisher | Format | Quant | Size | Link | Evidence |
|---|---|---|---|---|---|---|
Qwen3.8-27B-UD-Q5_K_M.gguf | Unsloth | gguf | UD-Q5_K_M | 18.41 GiB | source | SOURCE |
Qwen3.8-27B-UD-IQ4_XS.gguf | Unsloth | gguf | UD-IQ4_XS | 13.27 GiB | source | SOURCE |
VRAM (weights-only)
Not a full fit result. This classification considers artifact weights only. It does not include KV cache, runtime buffers, backend allocations, multimodal projectors, concurrency, or safety reserve.
| Component | Value | Evidence |
|---|---|---|
| Artifact weights | 18.41 GiB | SOURCE |
| KV cache | Not modeled | NOT KNOWN YET |
| Runtime buffers | Not modeled | NOT KNOWN YET |
| Safety reserve | Not modeled | NOT KNOWN YET |
| Weights-only memory class | 24gb+ | SOURCE POLICY |
Runtime support
Sources
- Hugging Face: https://huggingface.co/Qwen/Qwen3.8-27B
- Official: https://huggingface.co/Qwen/Qwen3.8-27B