Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
76 vs 74
Hardware Fit
46 vs 99
Quality Score
89 vs 63

Hardware

gemma4:31b llama3.2:3b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4 MaxCortex-A78AE
Cores166
RAM64 GB7 GB
GPUApple M4 MaxIntegrated / Unknown
OSmacOS 26.3.1Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:31b llama3.2:3b
Tokens/sec22.421.1
First chunk565 ms1032 ms
TTFT30.0 s1.0 s
Load time6.9 s8.4 s
Memory usage43.9 GB2.4 GB
Memory %69%32%

HW Fit Score Breakdown

gemma4:31b

Speed
30/50
TTFT
0/20
Memory
16/30

llama3.2:3b

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

Quality

gemma4:31b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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