Qwen3.5 27B
Qwen3.5 27B is an open-weights language model from Qwen, released February 23, 2026. It has 28B parameters (dense). The context window is 256K tokens. API price: $0.3 input / $2.4 output per million tokens.
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to …
Check it against your own PC →
Can you run Qwen3.5 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/Qwen3.5-27B-GGUF · bartowski/Qwen_Qwen3.5-27B-GGUF · Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF · lmstudio-community/Qwen3.5-27B-GGUF · wcn123/Qwen3.5-27B-WebNovel-Writer-zh-GGUF · unsloth/Qwen3.5-27B-MTP-GGUF
Benchmark results
Epoch AI has not published results for Qwen3.5 27B yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: Qwen/Qwen3.5-27B
More from Qwen
Qwen3.8 Omni Flash · Qwen3.8 Max (0902) · Qwen3.8 Flash · Qwen3.8 Flash Next · Qwen 3.8 27B · Qwen3.8-2.4T-A95B · Qwen 3.8 Max · Qwen3.7 Flash