Back to leaderboard

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 22, 2026 · Apple M2 Max

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Good

Mar 7, 2026 · AMD Ryzen 5 5500

Global Score
95 vs 71
Hardware Fit
94 vs 56
Quality Score
96 vs 78

Hardware

qwen3-30b-a3b-thin… qwen3.5:9b
MachineMac StudioSystem manufacturer
CPUApple M2 MaxAMD Ryzen 5 5500
Cores1212
RAM96 GB16 GB
GPUApple M2 MaxNVIDIA GeForce RTX 3060
OSmacOS 26.1Microsoft Windows 11 IoT Enterprise LTSC 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… qwen3.5:9b
Tokens/sec80.45.3
First chunk46 ms1624 ms
TTFT1.8 s1.6 s
Load timeN/A4.0 s
Memory usage21.2 GB7.9 GB
Memory %22%50%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
14/20
Memory
30/30

qwen3.5:9b

Speed
11/50
TTFT
20/20
Memory
25/30

Quality

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-30b-a3b-thin… details | View qwen3.5:9b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest