Qwen 3.8 27B
Qwen 3.8 27B is an open-weights language model from Qwen, released August 14, 2026. It has 28B parameters (dense). The context window is 256K tokens. On the Epoch Capabilities Index it scores 152.6, rank 58 of 256 rated models.
We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world coding & office workflows. - 262K native context, easily extendable to 1M tokens via YaRN. - Built for builders.
Check it against your own PC →
Can you run Qwen 3.8 27B locally?
The smallest common GPU it runs on is 12 GB of VRAM (with 32 GB of RAM): Q3_K_M, split GPU / CPU, roughly 5 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Very slow | IQ3_XXS (noticeable loss) | 5.2 GB | 7.1 GB | ~4 |
| 8 GB VRAM | Very slow | IQ3_XXS (noticeable loss) | 7.2 GB | 5.1 GB | ~5 |
| 12 GB VRAM | Runs, slowly | Q3_K_M (okay) | 11.2 GB | 4.1 GB | ~5 |
| 16 GB VRAM | Runs on GPU | IQ3_XXS (noticeable loss) | 12.3 GB | – | ~27 |
| 24 GB VRAM | Runs on GPU | Q5_K_M (excellent) | 21.4 GB | – | ~28 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 24.5 GB | – | ~45 |
Ready-made quantizations on Hugging Face: unsloth/Qwen3.8-27B-GGUF · huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF · cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF · JonathanColetti/Qwen3.8-27B-Uncensored-GGUF · byteshape/Qwen3.8-27B-GGUF · HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| SimpleBench | 52.2% |
| ProofBench | 16.0% |
Links
Announcement · Hugging Face: Qwen/Qwen3.8-27B · Epoch AI benchmarks
Models with a similar score
GPT-6 Luna · Claude Opus 4.6 · Grok 4.7 · Gemini 3.1 Pro · Qwen3.8 Max (0902) · DeepSeek V4 Pro 0813 · Muse Spark Open · Gemini 3.5 Flash
More from Qwen
Qwen3.8 Omni Flash · Qwen3.8 Max (0902) · Qwen3.8 Flash · Qwen3.8 Flash Next · Qwen3.8-2.4T-A95B · Qwen 3.8 Max · Qwen3.7 Flash · Qwen3.7-Plus