Alibaba
Qwen 3.5 397B A17B
最先端
Jun 2025公開日131K トークンコンテキストApache 2.0ライセンス100 卓越品質
Qwen 3.5 397B A17B (397B parameters) requires approximately 246.5 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 17B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 284 GB of VRAM.
はじめに
— コピー&ペーストでローカル実行Copy-paste commands to run Qwen 3.5 397B A17B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "Qwen/Qwen3.5-397B-A17B-Instruct" \
--hf-file "Qwen3.5-397B-A17B-Instruct-Q4_K_M.gguf" \
-c 4096 -ngl 99Quick specs
Parameters397B (17B active)
Architecturemoe (MoE)
Context131K tokens
Modalitytext
Min RAM154.8 GB
Rec. RAM242.2 GB (Q4_K_M)
LicenseApache 2.0
FamilyQwen
✓ Code✓ Chat✓ Reasoning
About this model
- •Flagship model — top-tier quality across coding, reasoning, math, and agentic tasks
- •397B total params with 17B active — strong quality with MoE inference efficiency
- •Requires multi-GPU or high-memory setups (150+ GB VRAM at Q4_K_M)
関連モデル
おすすめ
最適なハードウェア
Qwen 3.5 397B A17Bのおすすめ
このモデルを実行
量子化オプション
量子化レベル別VRAM推定値
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 154.8 GB | Low | — |
Q3_K_S | 3 | 194.5 GB | Low | — |
NVFP4 | 4 | 222.3 GB | Medium | — |
Q4_K_M | 4 | 242.2 GB | Medium | — |
Q5_K_M | 5 | 285.8 GB | High | — |
Q6_K | 6 | 325.5 GB | High | — |
Q8_0 | 8 | 424.8 GB | Very High | — |
F16 | 16 | 813.8 GB | Maximum | — |
Quality benchmarks
Qwen 3.5 397B A17B benchmark scores
Coding
SWE-bench Verified76.4%
HumanEval+—
Aider Polyglot—
LiveCodeBench83.6%
Reasoning
MMLU-Pro87.8%
GPQA Diamond88.4%
MATH-500—
ARC Challenge—
General
Chatbot Arena—
IFEval92.6%
Source: official · 2025-06-25
ハードウェア互換性
全ハードウェアの適合度推定
Computing compatibility...
メモリ内訳
Reference: RTX 2060 6GB
Weights242.2 GB
KV Cache2.9 GB
Runtime0.9 GB
Headroom0.6 GB
よくある質問
FAQ — Qwen 3.5 397B A17B
関連項目