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
phi3:14b
OLLAMA GGUFphi3 · 14.0B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
95 vs 63
Hardware Fit
94 vs 83
Quality Score
96 vs 55
Hardware
qwen3-30b-a3b-thin… phi3:14b
MachineMac StudioMacBook Air
CPUApple M2 MaxApple M4
Cores1210
RAM96 GB32 GB
GPUApple M2 MaxApple M4
OSmacOS 26.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… phi3:14b
Tokens/sec80.412.7
First chunk46 msN/A
TTFT1.8 s434 ms
Load timeN/A0.9 s
Memory usage21.2 GB17.7 GB
Memory %22%55%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
phi3:14b
Speed
23/50
TTFT
30/20
Memory
30/30
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
phi3:14b
Reasoning
14/20
Coding
2/20
Instruction
14/20
Structured
7/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate 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