Back to leaderboard

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
81 vs 37
Hardware Fit
100 vs 73
Quality Score
73 vs 22

Hardware

gemma3n:latest deepseek-r1:1.5b
MachineSupermicro AS -2015HS-TNRLENOVO 20L7CTO1WW
CPUAMD EPYC 9654P 96-Core ProcessorIntel Core™ i5-8350U
Cores648
RAM128 GB23 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Kaby Lake-R GT2 [UHD Graphics 620]
OSUbuntu 24.04.3 LTSFedora Linux 43
Archx64x64
Power Modeperformancelow-power

Performance

gemma3n:latest deepseek-r1:1.5b
Tokens/sec108.718.4
First chunk333 ms593 ms
TTFT333 ms30.0 s
Load time4.5 s3.8 s
Memory usage8.6 GB1.0 GB
Memory %7%4%

HW Fit Score Breakdown

gemma3n:latest

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

deepseek-r1:1.5b

Speed
43/50
TTFT
0/20
Memory
30/30

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-r1:1.5b

Reasoning
4/20
Coding
0/20
Instruction
5/20
Structured
3/15
Math
7/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Weak

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