Back to leaderboard

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

deepseek-r1:latest

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Not Rec.

Jun 25, 2026 · Cortex-A78AE

Global Score
81 vs 23
Hardware Fit
100 vs 70
Quality Score
73 vs 3

Hardware

gemma3n:latest deepseek-r1:latest
MachineSupermicro AS -2015HS-TNRNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD EPYC 9654P 96-Core ProcessorCortex-A78AE
Cores646
RAM128 GB7 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Integrated / Unknown
OSUbuntu 24.04.3 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modeperformancebalanced

Performance

gemma3n:latest deepseek-r1:latest
Tokens/sec108.79.8
First chunk333 ms1206 ms
TTFT333 ms1.2 s
Load time4.5 s17.8 s
Memory usage8.6 GB4.8 GB
Memory %7%65%

HW Fit Score Breakdown

gemma3n:latest

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

deepseek-r1:latest

Speed
32/50
TTFT
20/20
Memory
18/30

Quality

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

deepseek-r1:latest

Reasoning
0/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
2/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

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