Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
53 vs 65
Hardware Fit
81 vs 88
Quality Score
41 vs 55

Hardware

qwen3.5:4b-mlx qwen3.5-2b-mlx
MachineMac miniMac mini
CPUApple M2Apple M4 Pro
Cores814
RAM8 GB64 GB
GPUApple M2Apple M4 Pro
OSmacOS 26.5.2macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx qwen3.5-2b-mlx
Tokens/sec24.848.9
First chunk317 ms4208 ms
TTFT7.4 s4.2 s
Load time0.0 sN/A
Memory usage3.9 GB1.6 GB
Memory %49%3%

HW Fit Score Breakdown

qwen3.5:4b-mlx

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

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

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

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3.5:4b-mlx details | View qwen3.5-2b-mlx 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