qwen2.5-coder-7b-instruct-mlx

LM-STUDIO MLX

qwen2 · 7B · 4bit

Good

Mar 3, 2026 · Apple M4

ministral-3:3b

OLLAMA GGUF

mistral3 · 3.8B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score

79 vs 71

Hardware Fit

92 vs 99

Quality Score

73 vs 59

Hardware

qwen2.5-coder-7b-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-7b-i… ministral-3:3b

Tokens/sec22.542.2

First chunk529 ms189 ms

TTFT529 ms189 ms

Load timeN/A1.2 s

Memory usage4.0 GB7.0 GB

Memory %13%22%

HW Fit Score Breakdown

qwen2.5-coder-7b-instru…

Speed

44/50

TTFT

20/20

Memory

28/30

ministral-3:3b

Speed

50/50

TTFT

20/20

Memory

29/30

Quality

qwen2.5-coder-7b-instru…

Reasoning

10/20

Coding

18/20

Instruction

14/20

Structured

13/15

Math

9/15

Multilingual

9/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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-7b-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