Back to leaderboard

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
50 vs 62
Hardware Fit
97 vs 35
Quality Score
30 vs 73

Hardware

gemma3:270m qwen3.5-4b-mlx
MachineMacBook ProMac mini
CPUApple M3 ProApple M4 Pro
Cores1214
RAM36 GB64 GB
GPUApple M3 ProApple M4 Pro
OSmacOS 15.7.5macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma3:270m qwen3.5-4b-mlx
Tokens/sec239.20.0
First chunk127 ms5548 ms
TTFT127 ms5.5 s
Load time0.7 sN/A
Memory usage0.6 GB2.9 GB
Memory %2%5%

HW Fit Score Breakdown

gemma3:270m

Speed
50/50
TTFT
20/20
Memory
27/30

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

Quality

gemma3:270m

Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
8/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

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