qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Aug 20, 2026 · Apple M4 Max
gemma4:e2b-mlx
OLLAMA GGUFAug 25, 2026 · Apple M1 Pro
Global Score
96 vs 82
Hardware Fit
95 vs 99
Quality Score
96 vs 75
Hardware
qwen3-30b-a3b-thin… gemma4:e2b-mlx
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M1 Pro
Cores1610
RAM128 GB16 GB
GPUApple M4 MaxApple M1 Pro
OSmacOS 26.5.2macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… gemma4:e2b-mlx
Tokens/sec112.870.4
First chunk21 ms96 ms
TTFT1.5 s96 ms
Load time3.5 s2.5 s
Memory usage0.0 GB5.7 GB
Memory %0%36%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
gemma4:e2b-mlx
Speed
50/50
TTFT
20/20
Memory
29/30
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
gemma4:e2b-mlx
Reasoning
14/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest