Back to leaderboard

gemma4:e4b-mlx

OLLAMA GGUF
Not Rec.

Jul 7, 2026 · Apple M2 Pro

qwen2.5-coder-3b-instruct-mlx

LM-STUDIO MLX

qwen2 · 3B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score
78 vs 73
Hardware Fit
72 vs 100
Quality Score
81 vs 61

Hardware

gemma4:e4b-mlx qwen2.5-coder-3b-i…
MachineMacBook ProMacBook Air
CPUApple M2 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M2 ProApple M4
OSmacOS 26.5macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:e4b-mlx qwen2.5-coder-3b-i…
Tokens/sec26.952.3
First chunk222 ms285 ms
TTFT222 ms285 ms
Load time0.1 sN/A
Memory usage15.4 GB1.6 GB
Memory %96%5%

HW Fit Score Breakdown

gemma4:e4b-mlx

Speed
50/50
TTFT
20/20
Memory
2/30

qwen2.5-coder-3b-instru…

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

Quality

gemma4:e4b-mlx

Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen2.5-coder-3b-instru…

Reasoning
7/20
Coding
14/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View gemma4:e4b-mlx details | View qwen2.5-coder-3b-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