Back to leaderboard

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 22, 2026 · Apple M2 Max

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

Global Score
95 vs 66
Hardware Fit
94 vs 91
Quality Score
96 vs 55

Hardware

qwen3-30b-a3b-thin… qwen3.8-27b-mlx
MachineMac StudioMacBook Pro
CPUApple M2 MaxApple M5 Max
Cores1218
RAM96 GB64 GB
GPUApple M2 MaxApple M5 Max
OSmacOS 26.1macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… qwen3.8-27b-mlx
Tokens/sec80.433.2
First chunk46 ms7 ms
TTFT1.8 s311 ms
Load timeN/AN/A
Memory usage21.2 GB0.5 GB
Memory %22%1%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
14/20
Memory
30/30

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
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

qwen3.8-27b-mlx

Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest