Back to leaderboard

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

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

Hardware

llama-3.1-8b-instr… gemma3n:latest
MachineASUSSupermicro AS -2015HS-TNR
CPUAMD Ryzen 5 5500AMD EPYC 9654P 96-Core Processor
Cores1264
RAM31 GB128 GB
GPUNavi 44 [Radeon RX 9060 XT]GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSNobara Linux 43Ubuntu 24.04.3 LTS
Archx64x64
Power Modeperformanceperformance

Performance

llama-3.1-8b-instr… gemma3n:latest
Tokens/sec35.6108.7
First chunk52 ms333 ms
TTFT256 ms333 ms
Load timeN/A4.5 s
Memory usage8.6 GB8.6 GB
Memory %28%7%

HW Fit Score Breakdown

llama-3.1-8b-instruct

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

gemma3n:latest

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

Quality

llama-3.1-8b-instruct

Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
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