Qwen3.6 27B
Qwen3.6 27B is an open-weights language model from Qwen, released April 21, 2026. It has 28B parameters (dense). The context window is 256K tokens. On the Epoch Capabilities Index it scores 146.7, rank 87 of 256 rated models. API price: $0.6 input / $3.6 output per million tokens.
Following the launch of Qwen3.6-Plus and Qwen3.6-35B-A3B, we are excited to open-source Qwen3.6-27B — a dense 27-billion-parameter multimodal model at the scale the community has been asking for most.
Check it against your own PC →
Can you run Qwen3.6 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: prism-ml/Ternary-Bonsai-27B-gguf · unsloth/Qwen3.6-27B-GGUF · Alennnndy/Qwen3.6-27B-AWQ-4bit · FenomAI/Qwen3.6-27B-AWQ-INT4 · cyankiwi/Qwen3.6-27B-AWQ-INT4 · nvidia/Qwen3.6-27B-NVFP4
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Math | 40.1 | OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 91.1% |
| GPQA Diamond | 84.5% |
| FrontierMath (Tiers 1–3) | 36.9% |
| Mystery Game Puzzles | 0.0% |
Links
Announcement · Hugging Face: Qwen/Qwen3.6-27B · Epoch AI benchmarks
Models with a similar score
GLM-5.1 · DeepSeek-V4-Pro · GPT-5 · Grok 4.3 Beta · Qwen 3.6 Max (Preview) · GPT-5.4 Mini · Qwen 3.6 Plus · Kimi K2.5
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