Back to leaderboard

llama3.3:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-X925

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

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

Hardware

llama3.3:70b gemma3n:latest
MachineNVIDIA NVIDIA_DGX_SparkSupermicro AS -2015HS-TNR
CPUCortex-X925AMD EPYC 9654P 96-Core Processor
Cores2064
RAM122 GB128 GB
GPUDevice 2e12GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSUbuntu 24.04.4 LTSUbuntu 24.04.3 LTS
Archarm64x64
Power Modeperformanceperformance

Performance

llama3.3:70b gemma3n:latest
Tokens/sec4.6108.7
First chunk560 ms333 ms
TTFT560 ms333 ms
Load time13.8 s4.5 s
Memory usage49.5 GB8.6 GB
Memory %41%7%

HW Fit Score Breakdown

llama3.3:70b

Speed
4/50
TTFT
20/20
Memory
27/30

gemma3n:latest

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

Quality

llama3.3:70b

Reasoning
17/20
Coding
18/20
Instruction
12/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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