gemma3:270m
OLLAMA GGUFgemma3 · 268.10M · Q8_0
Mar 5, 2026 · Apple M3 Pro
qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
Global Score
50 vs 57
Hardware Fit
97 vs 61
Quality Score
30 vs 55
Hardware
gemma3:270m qwen3.5:9b
MachineMacBook ProAZW GTR Pro
CPUApple M3 ProAMD RYZEN AI MAX+ 395
Cores1232
RAM36 GB125 GB
GPUApple M3 ProAMD Radeon 8060S
OSmacOS 15.7.5Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
gemma3:270m qwen3.5:9b
Tokens/sec239.230.3
First chunk127 ms205 ms
TTFT127 ms8.7 s
Load time0.7 s5.6 s
Memory usage0.6 GB18.8 GB
Memory %2%15%
HW Fit Score Breakdown
gemma3:270m
Speed
50/50
TTFT
20/20
Memory
27/30
qwen3.5:9b
Speed
30/50
TTFT
1/20
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
qwen3.5:9b
Reasoning
17/20
Coding
2/20
Instruction
7/20
Structured
8/15
Math
12/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate 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