gemma3:270m
OLLAMA GGUFgemma3 · 268.10M · Q8_0
Mar 5, 2026 · Apple M3 Pro
rnj-1:8b
OLLAMA GGUFgemma3 · 8.3B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
50 vs 80
Hardware Fit
97 vs 93
Quality Score
30 vs 74
Hardware
gemma3:270m rnj-1:8b
MachineMacBook ProMacBook Pro
CPUApple M3 ProApple M1 Pro
Cores1210
RAM36 GB16 GB
GPUApple M3 ProApple M1 Pro
OSmacOS 15.7.5macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma3:270m rnj-1:8b
Tokens/sec239.222.3
First chunk127 ms404 ms
TTFT127 ms404 ms
Load time0.7 s3.7 s
Memory usage0.6 GB8.3 GB
Memory %2%52%
HW Fit Score Breakdown
gemma3:270m
Speed
50/50
TTFT
20/20
Memory
27/30
rnj-1:8b
Speed
49/50
TTFT
20/20
Memory
24/30
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
rnj-1:8b
Reasoning
12/20
Coding
19/20
Instruction
15/20
Structured
5/15
Math
14/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Weak Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest