AlibabaAlibaba

Qwen 3 0.6B

最先端
20.1Mダウンロード1.3KいいねApr 2025公開日33K トークンコンテキストApache 2.0ライセンス18 入門品質

Qwen 3 0.6B (0.6000000238418579B parameters) requires approximately 4.2 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 5 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 0.6B on your machine.

Run

ollama run qwen3:0.6b

Quick specs

Parameters0.6B
Architecturedense
Context33K tokens
Modalitytext
Min RAM0.2 GB
Rec. RAM0.4 GB (Q4_K_M)
LicenseApache 2.0
FamilyQwen
Chat

About this model

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:

  • Uniquely support of seamless switching between thinking mode: (for complex logical reasoning, math, and coding) and non-thinking mode (for...
  • Significantly enhancement in its reasoning capabilities: , surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking...
  • Superior human preference alignment: , excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a...
  • Expertise in agent capabilities: , enabling precise integration with external tools in both thinking and unthinking modes and achieving leading...
  • Support of 100+ languages and dialects: with strong capabilities for multilingual instruction following and translation

関連モデル

あなたのハードウェア

検出中...

おすすめ

最適なハードウェア

Qwen 3 0.6B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

QuantBitsVRAMQualityFit
Q2_K
2
0.2 GB
Low
Q3_K_S
3
0.3 GB
Low
NVFP4
4
0.3 GB
Medium
Q4_K_M
4
0.4 GB
Medium
Q5_K_M
5
0.4 GB
High
Q6_K
6
0.5 GB
High
Q8_0
8
0.6 GB
Very High
F16
16
1.2 GB
Maximum

Quality benchmarks

Qwen 3 0.6B benchmark scores

Benchmark verified

Reasoning

MMLU-Pro
GPQA Diamond
MATH-50077.6%
ARC Challenge

Source: community · 2025-04-27

ハードウェア互換性

全ハードウェアの適合度推定

カリキュレーターを開く

Computing compatibility...

メモリ内訳

Reference: RTX 2060 6GB

Weights0.4 GB
KV Cache0.9 GB
Runtime2.4 GB
Headroom0.6 GB

よくある質問

FAQ — Qwen 3 0.6B

関連項目