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
qwen2-57b:57B
OLLAMA GGUFqwen2moe · 57.4B · Q4_K_M
Aug 18, 2026 · Intel Core™ Ultra X7 358H
Global Score
95 vs 67
Hardware Fit
94 vs 51
Quality Score
96 vs 74
Hardware
qwen3-30b-a3b-thin… qwen2-57b:57B
MachineMac StudioGMKtec NucBox EVO-T2S
CPUApple M2 MaxIntel Core™ Ultra X7 358H
Cores1216
RAM96 GB64 GB
GPUApple M2 MaxIntel(R) Arc(TM) B390 GPU
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… qwen2-57b:57B
Tokens/sec80.48.6
First chunk46 ms1573 ms
TTFT1.8 s1.6 s
Load timeN/A29.0 s
Memory usage21.2 GB32.8 GB
Memory %22%52%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
qwen2-57b:57B
Speed
10/50
TTFT
17/20
Memory
24/30
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
qwen2-57b:57B
Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong 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