Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

Global Score
70 vs 81
Hardware Fit
73 vs 100
Quality Score
68 vs 73

Hardware

llama3.1:8b-instru… gemma3n:latest
Machine—Supermicro AS -2015HS-TNR
CPUC1-ProAMD EPYC 9654P 96-Core Processor
Cores064
RAM11 GB128 GB
GPUIntegrated / UnknownGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSunknown unknownUbuntu 24.04.3 LTS
Archarm64x64
Power Modeunknownperformance

Performance

llama3.1:8b-instru… gemma3n:latest
Tokens/sec6.5108.7
First chunk950 ms333 ms
TTFT950 ms333 ms
Load time11.5 s4.5 s
Memory usage4.4 GB8.6 GB
Memory %38%7%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

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

gemma3n:latest

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

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

gemma3n:latest

Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate 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