Open-Source Qwen Models

Match · Updated July 2026

The best open-weight Qwen model is Qwen3.6 27B (37.1 intelligence) — downloadable from Hugging Face and self-hostable. Qwen3.5-27B (33.8) and Qwen3.5 397B A17B (33.7) round out the top three.

37.1Intelligence

$0.300Input /M

262KContext

The best open-source AI models — open-weight, downloadable from Hugging Face and self-hostable — ranked by intelligence. Open-source alternatives to proprietary frontier models.

1
qwen3.6-27b
ReasoningToolsJSON+137.1 intel · $0.300/M · 262K ctx
37.1
Intelligence
2
qwen3.5-27b
ReasoningToolsJSON+133.8 intel · $0.195/M · 262K ctx
33.8
Intelligence
3
qwen3.5-397b-a17b
ReasoningToolsJSON+133.7 intel · $0.390/M · 262K ctx
33.7
Intelligence
4
qwen3.5-122b-a10b
ReasoningToolsJSON+132.3 intel · $0.260/M · 262K ctx
32.3
Intelligence
5
qwen3.6-35b-a3b
ReasoningToolsJSON+131.6 intel · $0.140/M · 262K ctx
31.6
Intelligence
6
qwen3.5-35b-a3b
ReasoningToolsJSON+129.3 intel · $0.140/M · 262K ctx
29.3
Intelligence
7
qwen3.5-9b
ReasoningToolsJSON+121.4 intel · $0.100/M · 262K ctx
21.4
Intelligence
8
qwen3-coder-next
ToolsJSON21.1 intel · $0.120/M · 262K ctx
21.1
Intelligence
9
qwen3-vl-235b-a22b-instruct
ToolsJSONVision14.3 intel · $0.210/M · 262K ctx
14.3
Intelligence
10
qwen3-next-80b-a3b-instruct
ToolsJSON13.7 intel · $0.100/M · 262K ctx
13.7
Intelligence
11
qwen3-coder-30b-a3b-instruct
ToolsJSON13.6 intel · $0.070/M · 262K ctx
13.6
Intelligence
12
qwen3-vl-32b-instruct
ToolsJSONVision11.1 intel · $0.104/M · 131K ctx
11.1
Intelligence
13
qwen3-vl-30b-a3b-instruct
ToolsJSONVision10.0 intel · $0.150/M · 262K ctx
10.0
Intelligence
14
qwen-2.5-72b-instruct
ToolsJSON9.6 intel · $0.360/M · 33K ctx
9.6
Intelligence
15
qwen3-vl-8b-instruct
ToolsJSONVision8.4 intel · $0.117/M · 262K ctx
8.4
Intelligence
16
qwen-2.5-coder-32b-instruct
7.1 intel · $0.660/M · 33K ctx
7.1
Intelligence
17
qwen3-vl-8b-thinking
ReasoningToolsJSON+1$0.180/M · 131K ctx
—
Intelligence
18
qwen3-vl-30b-a3b-thinking
ReasoningToolsJSON+1$0.200/M · 262K ctx
—
Intelligence
19
qwen3-vl-235b-a22b-thinking
ReasoningToolsJSON+1$0.400/M · 131K ctx
—
Intelligence
20
qwen3-next-80b-a3b-thinking
ReasoningToolsJSON$0.150/M · 262K ctx
—
Intelligence
21
qwen3-30b-a3b-thinking-2507
ReasoningToolsJSON$0.200/M · 82K ctx
—
Intelligence
22
qwen3-30b-a3b-instruct-2507
ToolsJSON$0.048/M · 262K ctx
—
Intelligence
23
qwen3-235b-a22b-thinking-2507
ReasoningToolsJSON$0.300/M · 262K ctx
—
Intelligence
24
qwen3-coder
ToolsJSON$0.300/M · 262K ctx
—
Intelligence
25
qwen3-235b-a22b-2507
ToolsJSON$0.090/M · 262K ctx
—
Intelligence

Frequently asked

What is the best open-source Qwen model?

The best open-weight Qwen model is Qwen3.6 27B (37.1 intelligence) — downloadable from Hugging Face and self-hostable. Qwen3.5-27B (33.8) and Qwen3.5 397B A17B (33.7) round out the top three.

What's a good alternative to Qwen3.6 27B?

Qwen3.5-27B (33.8) is the closest alternative on this metric, followed by Qwen3.5 397B A17B (33.7). See the full ranking above for the tradeoffs.

How many Qwen models are there?

modelgrep tracks 48 Qwen models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Qwen3.7 Max. 25 of them qualify for this ranking.

More Qwen rankings

Qwen: Smartest LLMs Qwen: Best LLMs for Coding Qwen: Best LLMs for Design & Frontend Qwen: Fastest LLMs Qwen: Lowest-Latency LLMs Qwen: Cheapest LLMs Qwen: Best Free LLMs Qwen: Best Reasoning LLMs Qwen: Best Vision LLMs Qwen: Best LLMs for Agents Qwen: Longest-Context LLMs Qwen: Best LLMs for Writing Qwen: Best LLMs for Math & Science Qwen: Best LLMs for RAG Qwen: Best LLMs for SQL & Data Analysis Qwen: Best LLMs for Roleplay Qwen: Best Uncensored LLMs

All rankings

Small & Fast LLMs Best Local LLMs Smartest LLMs Best LLMs for Coding Best LLMs for Design & Frontend Fastest LLMs Lowest-Latency LLMs Cheapest LLMs Best Free LLMs Best Reasoning LLMs Best Vision LLMs Best LLMs for Agents Longest-Context LLMs Best LLMs for Writing Best LLMs for Math & Science Best LLMs for RAG Best LLMs for SQL & Data Analysis Best LLMs for Roleplay Best Uncensored LLMs