Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is an open-weights language model from Qwen, released February 13, 2026. It has 403B parameters (mixture-of-experts, 17B active). The context window is 256K tokens. On the Epoch Capabilities Index it scores 147.9, rank 77 of 256 rated models. API price: $0.6 input / $3.6 output per million tokens.
We are delighted to announce the official release of Qwen3.5, introducing the open-weight of the first model in the Qwen3.5 series, namely Qwen3.5-397B-A17B. As a native vision-language model, Qwen3.5-397B-A17B demonstrates outstanding results across a full range of benchmark evaluations, including reasoning, coding, …
Check it against your own PC →
Can you run Qwen3.5 397B-A17B locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. 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 | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Too large | – | – | – | – |
Ready-made quantizations on Hugging Face: unsloth/Qwen3.5-397B-A17B-GGUF · bartowski/Qwen_Qwen3.5-397B-A17B-GGUF · unsloth/Qwen3.5-397B-A17B-MTP-GGUF · mudler/Qwen3.5-397B-A17B-APEX-GGUF · cyankiwi/Qwen3.5-397B-A17B-AWQ-4bit · QuantTrio/Qwen3.5-397B-A17B-AWQ
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Math | 38.1 | OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 88.9% |
| GPQA Diamond | 85.2% |
| FrontierMath (Tiers 1–3) | 32.9% |
| Mystery Game Puzzles | 9.7% |
Links
Announcement · Hugging Face: Qwen/Qwen3.5-397B-A17B · Epoch AI benchmarks
Models with a similar score
Kimi K2.6 · GPT-5 Pro · Kimi K2.7 Code · GPT-5.1 · Beam 1.0 · Inkling-Small · GLM-5.1 · DeepSeek-V4-Pro
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