Back to leaderboard

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

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

Hardware

deepseek-r1:1.5b gemma3n:latest
MachineLENOVO 20L7CTO1WWSupermicro AS -2015HS-TNR
CPUIntel Core™ i5-8350UAMD EPYC 9654P 96-Core Processor
Cores864
RAM23 GB128 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSFedora Linux 43Ubuntu 24.04.3 LTS
Archx64x64
Power Modelow-powerperformance

Performance

deepseek-r1:1.5b gemma3n:latest
Tokens/sec18.4108.7
First chunk593 ms333 ms
TTFT30.0 s333 ms
Load time3.8 s4.5 s
Memory usage1.0 GB8.6 GB
Memory %4%7%

HW Fit Score Breakdown

deepseek-r1:1.5b

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

gemma3n:latest

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

Quality

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

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