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
qwen/qwen3.8-27b
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Aug 19, 2026 · Apple M4 Max
Global Score
95 vs 83
Hardware Fit
94 vs 68
Quality Score
96 vs 90
Hardware
qwen3-30b-a3b-thin… qwen/qwen3.8-27b
MachineMac StudioMacBook Pro
CPUApple M2 MaxApple M4 Max
Cores1216
RAM96 GB128 GB
GPUApple M2 MaxApple M4 Max
OSmacOS 26.1macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… qwen/qwen3.8-27b
Tokens/sec80.427.6
First chunk46 ms10 ms
TTFT1.8 s4.6 s
Load timeN/AN/A
Memory usage21.2 GB21.0 GB
Memory %22%16%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
qwen/qwen3.8-27b
Speed
32/50
TTFT
6/20
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
qwen/qwen3.8-27b
Reasoning
19/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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