llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
gemma3:270m
OLLAMA GGUFgemma3 · 268.10M · Q8_0
Mar 5, 2026 · Apple M3 Pro
Global Score
46 vs 50
Hardware Fit
61 vs 97
Quality Score
40 vs 30
Hardware
llama3.1:8b gemma3:270m
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M3 Pro
Cores612
RAM7 GB36 GB
GPUIntegrated / UnknownApple M3 Pro
OSUbuntu 22.04.5 LTSmacOS 15.7.5
Archarm64arm64
Power Modebalancedbalanced
Performance
llama3.1:8b gemma3:270m
Tokens/sec7.8239.2
First chunk1625 ms127 ms
TTFT1.6 s127 ms
Load time21.8 s0.7 s
Memory usage5.2 GB0.6 GB
Memory %71%2%
HW Fit Score Breakdown
llama3.1:8b
Speed
26/50
TTFT
20/20
Memory
15/30
gemma3:270m
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
llama3.1:8b
Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong
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
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