Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

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

Global Score
59 vs 95
Hardware Fit
63 vs 94
Quality Score
58 vs 96

Hardware

qwen3.8-27b-mlx qwen3-30b-a3b-thin…
MachineMacBook ProMac Studio
CPUApple M5 MaxApple M2 Max
Cores1812
RAM64 GB96 GB
GPUApple M5 MaxApple M2 Max
OSmacOS 27.0macOS 26.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.8-27b-mlx qwen3-30b-a3b-thin…
Tokens/sec18.380.4
First chunk4 ms46 ms
TTFT530 ms1.8 s
Load timeN/AN/A
Memory usage38.5 GB21.2 GB
Memory %60%22%

HW Fit Score Breakdown

qwen3.8-27b-mlx

Speed
23/50
TTFT
20/20
Memory
20/30

qwen3-30b-a3b-thinking-…

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

Quality

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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

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