Back to leaderboard

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

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

Hardware

llama3.2:3b gemma4:31b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M4 Max
Cores616
RAM7 GB64 GB
GPUIntegrated / UnknownApple M4 Max
OSUbuntu 22.04.5 LTSmacOS 26.3.1
Archarm64arm64
Power Modebalancedbalanced

Performance

llama3.2:3b gemma4:31b
Tokens/sec21.122.4
First chunk1032 ms565 ms
TTFT1.0 s30.0 s
Load time8.4 s6.9 s
Memory usage2.4 GB43.9 GB
Memory %32%69%

HW Fit Score Breakdown

llama3.2:3b

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

gemma4:31b

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

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

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

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