Back to leaderboard

vicuna:13b

OLLAMA GGUF

llama · 13B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
59 vs 76
Hardware Fit
84 vs 92
Quality Score
48 vs 69

Hardware

vicuna:13b gemma3:4b
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

vicuna:13b gemma3:4b
Tokens/sec13.415.0
First chunkN/A2380 ms
TTFT438 ms2.4 s
Load time0.6 s13.6 s
Memory usage10.3 GB2.6 GB
Memory %32%35%

HW Fit Score Breakdown

vicuna:13b

Speed
24/50
TTFT
30/20
Memory
30/30

gemma3:4b

Speed
45/50
TTFT
18/20
Memory
29/30

Quality

vicuna:13b

Reasoning
7/20
Coding
5/20
Instruction
12/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

gemma3:4b

Reasoning
11/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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