qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 22, 2026 · Apple M2 Max
unsloth/gemma-4-26b-a4b-it
LM-STUDIO GGUFgemma4 · 26B · Q3_K_M
Apr 5, 2026 · Apple M4
Global Score
95 vs 90
Hardware Fit
94 vs 85
Quality Score
96 vs 92
Hardware
qwen3-30b-a3b-thin… unsloth/gemma-4-26…
MachineMac StudioMac mini
CPUApple M2 MaxApple M4
Cores1210
RAM96 GB24 GB
GPUApple M2 MaxApple M4
OSmacOS 26.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… unsloth/gemma-4-26…
Tokens/sec80.424.9
First chunk46 ms15 ms
TTFT1.8 s817 ms
Load timeN/AN/A
Memory usage21.2 GB16.8 GB
Memory %22%70%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
unsloth/gemma-4-26b-a4b…
Speed
50/50
TTFT
20/20
Memory
15/30
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
unsloth/gemma-4-26b-a4b…
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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