llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Mar 2, 2026 · Apple M4
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
74 vs 46
Hardware Fit
100 vs 61
Quality Score
63 vs 40
Hardware
llama3.2:3b llama3.1:8b
MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
llama3.2:3b llama3.1:8b
Tokens/sec44.17.8
First chunkN/A1625 ms
TTFT178 ms1.6 s
Load time0.8 s21.8 s
Memory usage7.0 GB5.2 GB
Memory %22%71%
HW Fit Score Breakdown
llama3.2:3b
Speed
40/50
TTFT
30/20
Memory
30/30
llama3.1:8b
Speed
26/50
TTFT
20/20
Memory
15/30
Quality
llama3.2:3b
Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
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
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