Back to leaderboard

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Marginal

Jun 26, 2026 · Cortex-A78AE

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

Global Score
46 vs 81
Hardware Fit
61 vs 100
Quality Score
40 vs 73

Hardware

llama3.1:8b gemma3n:latest
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperSupermicro AS -2015HS-TNR
CPUCortex-A78AEAMD EPYC 9654P 96-Core Processor
Cores664
RAM7 GB128 GB
GPUIntegrated / UnknownGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSUbuntu 22.04.5 LTSUbuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance

Performance

llama3.1:8b gemma3n:latest
Tokens/sec7.8108.7
First chunk1625 ms333 ms
TTFT1.6 s333 ms
Load time21.8 s4.5 s
Memory usage5.2 GB8.6 GB
Memory %71%7%

HW Fit Score Breakdown

llama3.1:8b

Speed
26/50
TTFT
20/20
Memory
15/30

gemma3n:latest

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

Quality

llama3.1:8b

Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor 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