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 20, 2026 · Apple M2 Max

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

Global Score
97 vs 50
Hardware Fit
95 vs 97
Quality Score
98 vs 30

Hardware

qwen3-30b-a3b-thin… gemma3:270m
MachineMac StudioMacBook Pro
CPUApple M2 MaxApple M3 Pro
Cores1212
RAM96 GB36 GB
GPUApple M2 MaxApple M3 Pro
OSmacOS 26.1macOS 15.7.5
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… gemma3:270m
Tokens/sec79.6239.2
First chunk11 ms127 ms
TTFT1.7 s127 ms
Load time7.1 s0.7 s
Memory usage0.0 GB0.6 GB
Memory %0%2%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
15/20
Memory
30/30

gemma3:270m

Speed
50/50
TTFT
20/20
Memory
27/30

Quality

qwen3-30b-a3b-thinking-…

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

gemma3:270m

Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
8/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak

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