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

LM-STUDIO MLX

qwen2 · 7B · 4bit

Good

Mar 3, 2026 · Apple M4

qwen3.6:35b-a3b-coding-nvfp4

OLLAMA GGUF

nvfp4

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score

79 vs 76

Hardware Fit

92 vs 77

Quality Score

73 vs 76

Hardware

qwen2.5-coder-7b-i… qwen3.6:35b-a3b-co…

MachineMacBook AirMacBook Pro

CPUApple M4Apple M4 Pro

Cores1014

RAM32 GB48 GB

GPUApple M4Apple M4 Pro

OSmacOS 26.3macOS 26.4.1

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen2.5-coder-7b-i… qwen3.6:35b-a3b-co…

Tokens/sec22.572.7

First chunk529 ms147 ms

TTFT529 ms30.0 s

Load timeN/A5.7 s

Memory usage4.0 GB19.6 GB

Memory %13%41%

HW Fit Score Breakdown

qwen2.5-coder-7b-instru…

Speed

44/50

TTFT

20/20

Memory

28/30

qwen3.6:35b-a3b-coding-…

Speed

50/50

TTFT

0/20

Memory

27/30

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

qwen3.6:35b-a3b-coding-…

Reasoning

19/20

Coding

9/20

Instruction

13/20

Structured

12/15

Math

13/15

Multilingual

10/10

Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

View qwen2.5-coder-7b-i… details | View qwen3.6:35b-a3b-co… 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