Back to leaderboard

phi4-mini:latest

OLLAMA GGUF

phi3 · 3.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
74 vs 74
Hardware Fit
98 vs 99
Quality Score
63 vs 63

Hardware

phi4-mini:latest llama3.2:3b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUCortex-A78AECortex-A78AE
Cores66
RAM7 GB7 GB
GPUIntegrated / UnknownIntegrated / Unknown
OSUbuntu 22.04.5 LTSUbuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

phi4-mini:latest llama3.2:3b
Tokens/sec18.421.1
First chunk1078 ms1032 ms
TTFT1.1 s1.0 s
Load time6.4 s8.4 s
Memory usage2.9 GB2.4 GB
Memory %39%32%

HW Fit Score Breakdown

phi4-mini:latest

Speed
50/50
TTFT
20/20
Memory
28/30

llama3.2:3b

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

phi4-mini:latest

Reasoning
13/20
Coding
11/20
Instruction
14/20
Structured
11/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Strong

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

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest