Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

ministral-3:8b

OLLAMA GGUF

mistral3 · 8.9B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
66 vs 76
Hardware Fit
91 vs 89
Quality Score
55 vs 71

Hardware

qwen3.8-27b-mlx ministral-3:8b
MachineMacBook ProMacBook Air
CPUApple M5 MaxApple M4
Cores1810
RAM64 GB32 GB
GPUApple M5 MaxApple M4
OSmacOS 27.0macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.8-27b-mlx ministral-3:8b
Tokens/sec33.219.5
First chunk7 ms328 ms
TTFT311 ms328 ms
Load timeN/A1.5 s
Memory usage0.5 GB10.6 GB
Memory %1%33%

HW Fit Score Breakdown

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
Memory
30/30

ministral-3:8b

Speed
39/50
TTFT
20/20
Memory
30/30

Quality

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

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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest