Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

gemma3:12b

OLLAMA GGUF

gemma3 · 12.2B · Q4_K_M

Excellent

Mar 2, 2026 · Apple M4

Global Score
53 vs 80
Hardware Fit
81 vs 83
Quality Score
41 vs 78

Hardware

qwen3.5:4b-mlx gemma3:12b
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 gemma3:12b
Tokens/sec24.812.7
First chunk317 msN/A
TTFT7.4 s560 ms
Load time0.0 s2.8 s
Memory usage3.9 GB11.0 GB
Memory %49%34%

HW Fit Score Breakdown

qwen3.5:4b-mlx

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

gemma3:12b

Speed
23/50
TTFT
30/20
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

gemma3:12b

Reasoning
14/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:4b-mlx details | View gemma3:12b 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