Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

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

LM-STUDIO MLX

qwen2 · 7B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
53 vs 79
Hardware Fit
81 vs 92
Quality Score
41 vs 73

Hardware

qwen3.5:4b-mlx qwen2.5-coder-7b-i…
MachineMac miniMacBook Air
CPUApple M2Apple M4
Cores810
RAM8 GB32 GB
GPUApple M2Apple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx qwen2.5-coder-7b-i…
Tokens/sec24.822.5
First chunk317 ms529 ms
TTFT7.4 s529 ms
Load time0.0 sN/A
Memory usage3.9 GB4.0 GB
Memory %49%13%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
25/30

qwen2.5-coder-7b-instru…

Speed
44/50
TTFT
20/20
Memory
28/30

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

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
View qwen3.5:4b-mlx details | View qwen2.5-coder-7b-i… 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