Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
70 vs 76
Hardware Fit
73 vs 92
Quality Score
68 vs 69

Hardware

llama3.1:8b-instru… gemma3:4b
Machine—NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUC1-ProCortex-A78AE
Cores06
RAM11 GB7 GB
GPUIntegrated / UnknownIntegrated / Unknown
OSunknown unknownUbuntu 22.04.5 LTS
Archarm64arm64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… gemma3:4b
Tokens/sec6.515.0
First chunk950 ms2380 ms
TTFT950 ms2.4 s
Load time11.5 s13.6 s
Memory usage4.4 GB2.6 GB
Memory %38%35%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

Speed
25/50
TTFT
20/20
Memory
28/30

gemma3:4b

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

Quality

llama3.1:8b-instruct-q4…

Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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