Back to leaderboard

gemma4:e4b-mlx

OLLAMA GGUF
Excellent

Jul 7, 2026 · Apple M2 Pro

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Mar 16, 2026 · Intel Core™ i7-4771

Global Score
85 vs 65
Hardware Fit
95 vs 92
Quality Score
81 vs 54

Hardware

gemma4:e4b-mlx qwen2.5:1.5b
MachineMacBook ProiMac
CPUApple M2 ProIntel Core™ i7-4771
Cores108
RAM16 GB32 GB
GPUApple M2 ProNVIDIA GeForce GTX 780M
OSmacOS 26.5macOS 15.7.3
Archarm64x64
Power Modebalancedbalanced

Performance

gemma4:e4b-mlx qwen2.5:1.5b
Tokens/sec47.319.6
First chunk258 ms690 ms
TTFT258 ms690 ms
Load time5.1 s21.4 s
Memory usage7.9 GB1.0 GB
Memory %49%3%

HW Fit Score Breakdown

gemma4:e4b-mlx

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

qwen2.5:1.5b

Speed
42/50
TTFT
20/20
Memory
30/30

Quality

gemma4:e4b-mlx

Reasoning
15/20
Coding
18/20
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

qwen2.5:1.5b

Reasoning
8/20
Coding
9/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
View gemma4:e4b-mlx details | View qwen2.5:1.5b 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