Back to leaderboard

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

Global Score
50 vs 77
Hardware Fit
97 vs 90
Quality Score
30 vs 71

Hardware

gemma3:270m spark-x2.5-4b
MachineMacBook ProASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUApple M3 ProAMD Ryzen 7 4800H
Cores1216
RAM36 GB15 GB
GPUApple M3 ProAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 15.7.5Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

gemma3:270m spark-x2.5-4b
Tokens/sec239.248.9
First chunk127 ms20 ms
TTFT127 ms168 ms
Load time0.7 sN/A
Memory usage0.6 GB9.4 GB
Memory %2%61%

HW Fit Score Breakdown

gemma3:270m

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

spark-x2.5-4b

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

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

spark-x2.5-4b

Reasoning
13/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View gemma3:270m details | View spark-x2.5-4b 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