llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
hf.co/openbmb/MiniCPM5-1B-GGUF:F16
OLLAMA GGUFllama · 1.08B · F16
Aug 26, 2026 · Apple M1 Pro
Global Score
74 vs 62
Hardware Fit
99 vs 100
Quality Score
63 vs 45
Hardware
llama3.2:3b hf.co/openbmb/Mini…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M1 Pro
Cores610
RAM7 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSUbuntu 22.04.5 LTSmacOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
llama3.2:3b hf.co/openbmb/Mini…
Tokens/sec21.189.1
First chunk1032 ms42 ms
TTFT1.0 s42 ms
Load time8.4 s1.6 s
Memory usage2.4 GB3.9 GB
Memory %32%25%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
hf.co/openbmb/MiniCPM5-…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
llama3.2:3b
Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
hf.co/openbmb/MiniCPM5-…
Reasoning
16/20
Coding
9/20
Instruction
4/20
Structured
0/15
Math
14/15
Multilingual
2/10
Reasoning: Strong Coding: Weak Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
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