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
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Jun 25, 2026 · Apple M4 Pro
Global Score
95 vs 79
Hardware Fit
94 vs 98
Quality Score
96 vs 71
Hardware
qwen3-30b-a3b-thin… ministral-3:8b
MachineMac StudioMac mini
CPUApple M2 MaxApple M4 Pro
Cores1212
RAM96 GB24 GB
GPUApple M2 MaxApple M4 Pro
OSmacOS 26.1macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… ministral-3:8b
Tokens/sec80.441.4
First chunk46 ms257 ms
TTFT1.8 s257 ms
Load timeN/A5.2 s
Memory usage21.2 GB9.0 GB
Memory %22%38%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
ministral-3:8b
Speed
50/50
TTFT
20/20
Memory
28/30
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
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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