Back to leaderboard

qwen2.5-coder-3b-instruct-mlx

LM-STUDIO MLX

qwen2 · 3B · 4bit

Good

Mar 4, 2026 · Apple M4

ministral-3:3b

OLLAMA GGUF

mistral3 · 3.8B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
73 vs 71
Hardware Fit
100 vs 99
Quality Score
61 vs 59

Hardware

qwen2.5-coder-3b-i… ministral-3:3b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen2.5-coder-3b-i… ministral-3:3b
Tokens/sec52.342.2
First chunk285 ms189 ms
TTFT285 ms189 ms
Load timeN/A1.2 s
Memory usage1.6 GB7.0 GB
Memory %5%22%

HW Fit Score Breakdown

qwen2.5-coder-3b-instru…

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

ministral-3:3b

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

qwen2.5-coder-3b-instru…

Reasoning
7/20
Coding
14/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

ministral-3:3b

Reasoning
5/20
Coding
16/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen2.5-coder-3b-i… details | View ministral-3:3b details

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