Alibaba
Qwen3-Coder-Next
最先端
937.9Kダウンロード1.4KいいねJan 2026公開日256K トークンコンテキストApache 2.0ライセンス93 卓越品質
Qwen3-Coder-Next (80B parameters) requires approximately 52.1 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 3B 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 60 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 Qwen3-Coder-Next on your machine.
Run
ollama run qwen3-coder-nextQuick specs
Parameters80B (3B active)
Architecturemoe (MoE)
Context256K tokens
Modalitytext
Min RAM31.2 GB
Rec. RAM48.8 GB (Q4_K_M)
LicenseApache 2.0
FamilyQwen Coder
✓ Code✓ Reasoning
About this model
- •Super Efficient with Significant Performance: With only 3B activated parameters (80B total parameters), it achieves performance comparable to...
- •Advanced Agentic Capabilities: Through an elaborate training recipe, it excels at long-horizon reasoning, complex tool usage, and recovery from...
- •Versatile Integration with Real-World IDE: Its 256k context length, combined with adaptability to various scaffold templates, enables seamless...
関連モデル
おすすめ
最適なハードウェア
Qwen3-Coder-Next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 | 31.2 GB | Low | — |
Q3_K_S | 3 | 39.2 GB | Low | — |
NVFP4 | 4 | 44.8 GB | Medium | — |
Q4_K_M | 4 | 48.8 GB | Medium | — |
Q5_K_M | 5 | 57.6 GB | High | — |
Q6_K | 6 | 65.6 GB | High | — |
Q8_0 | 8 | 85.6 GB | Very High | — |
F16 | 16 | 164.0 GB | Maximum | — |
Quality benchmarks
Qwen3-Coder-Next benchmark scores
Coding
SWE-bench Verified70.6%
HumanEval+—
Aider Polyglot—
LiveCodeBench74.5%
Reasoning
MMLU-Pro78.4%
GPQA Diamond—
MATH-500—
ARC Challenge—
Source: official · 2026-01-30
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
Weights48.8 GB
KV Cache1.5 GB
Runtime1.2 GB
Headroom0.6 GB
よくある質問
FAQ — Qwen3-Coder-Next
関連項目