Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

Global Score
53 vs 85
Hardware Fit
82 vs 64
Quality Score
41 vs 94

Hardware

qwen3.5:4b-mlx gemma-4-31b-it-mlx
MachineMac miniMacBook Pro
CPUApple M2Apple M4 Max
Cores816
RAM8 GB128 GB
GPUApple M2Apple M4 Max
OSmacOS 26.5.2macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx gemma-4-31b-it-mlx
Tokens/sec24.713.6
First chunk302 ms16 ms
TTFT7.4 s558 ms
Load time3.2 s12.3 s
Memory usage3.8 GB0.0 GB
Memory %47%0%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

gemma-4-31b-it-mlx

Speed
14/50
TTFT
20/20
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

gemma-4-31b-it-mlx

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:4b-mlx details | View gemma-4-31b-it-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