Back to leaderboard

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

yi:6b

OLLAMA GGUF

llama · 6B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score
50 vs 77
Hardware Fit
97 vs 100
Quality Score
30 vs 67

Hardware

gemma3:270m yi:6b
MachineMacBook ProMacBook Air
CPUApple M3 ProApple M4
Cores1210
RAM36 GB32 GB
GPUApple M3 ProApple M4
OSmacOS 15.7.5macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma3:270m yi:6b
Tokens/sec239.227.6
First chunk127 msN/A
TTFT127 ms210 ms
Load time0.7 s0.4 s
Memory usage0.6 GB3.6 GB
Memory %2%11%

HW Fit Score Breakdown

gemma3:270m

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

yi:6b

Speed
40/50
TTFT
30/20
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

yi:6b

Reasoning
11/20
Coding
12/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
6/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate
View gemma3:270m details | View yi:6b 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