gemma3:270m
OLLAMA GGUFgemma3 · 268.10M · Q8_0
Mar 5, 2026 · Apple M3 Pro
devstral-small-2-24b-instruct-2512
LM-STUDIO GGUFmistral3 · 24B · IQ4_XS
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
50 vs 81
Hardware Fit
97 vs 80
Quality Score
30 vs 81
Hardware
gemma3:270m devstral-small-2-2…
MachineMacBook ProSystem manufacturer
CPUApple M3 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1216
RAM36 GB31 GB
GPUApple M3 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 15.7.5Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance
Performance
gemma3:270m devstral-small-2-2…
Tokens/sec239.221.5
First chunk127 ms12 ms
TTFT127 ms212 ms
Load time0.7 sN/A
Memory usage0.6 GB15.9 GB
Memory %2%51%
HW Fit Score Breakdown
gemma3:270m
Speed
50/50
TTFT
20/20
Memory
27/30
devstral-small-2-24b-in…
Speed
35/50
TTFT
20/20
Memory
25/30
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
devstral-small-2-24b-in…
Reasoning
16/20
Coding
17/20
Instruction
17/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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