Back to leaderboard

ministral-3:8b

OLLAMA GGUF

mistral3 · 8.9B · Q4_K_M

Good

Jun 25, 2026 · Apple M4 Pro

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

Global Score
79 vs 66
Hardware Fit
98 vs 91
Quality Score
71 vs 55

Hardware

ministral-3:8b qwen3.8-27b-mlx
MachineMac miniMacBook Pro
CPUApple M4 ProApple M5 Max
Cores1218
RAM24 GB64 GB
GPUApple M4 ProApple M5 Max
OSmacOS 15.6.1macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

ministral-3:8b qwen3.8-27b-mlx
Tokens/sec41.433.2
First chunk257 ms7 ms
TTFT257 ms311 ms
Load time5.2 sN/A
Memory usage9.0 GB0.5 GB
Memory %38%1%

HW Fit Score Breakdown

ministral-3:8b

Speed
50/50
TTFT
20/20
Memory
28/30

qwen3.8-27b-mlx

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

Quality

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

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