Back to leaderboard

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Good

Mar 5, 2026 · Apple M1 Max

Global Score
50 vs 62
Hardware Fit
97 vs 100
Quality Score
30 vs 46

Hardware

gemma3:270m qwen3.5:0.8b
MachineMacBook ProMacBook Pro
CPUApple M3 ProApple M1 Max
Cores1210
RAM36 GB32 GB
GPUApple M3 ProApple M1 Max
OSmacOS 15.7.5macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma3:270m qwen3.5:0.8b
Tokens/sec239.267.6
First chunk127 ms209 ms
TTFT127 ms209 ms
Load time0.7 s1.9 s
Memory usage0.6 GB2.6 GB
Memory %2%8%

HW Fit Score Breakdown

gemma3:270m

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

qwen3.5:0.8b

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

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

qwen3.5:0.8b

Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View gemma3:270m details | View qwen3.5:0.8b 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