Back to leaderboard

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

falcon-h1-tiny-90m-instruct

LM-STUDIO GGUF

falcon-h1 · 90M · Q4_K_M

Marginal

Mar 8, 2026 · Intel Core™ i5-5300U

Global Score
81 vs 43
Hardware Fit
100 vs 99
Quality Score
73 vs 19

Hardware

gemma3n:latest falcon-h1-tiny-90m…
MachineSupermicro AS -2015HS-TNRLENOVO 20BUS00700
CPUAMD EPYC 9654P 96-Core ProcessorIntel Core™ i5-5300U
Cores644
RAM128 GB16 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Intel(R) HD Graphics 5500
OSUbuntu 24.04.3 LTSMicrosoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modeperformancebalanced

Performance

gemma3n:latest falcon-h1-tiny-90m…
Tokens/sec108.767.8
First chunk333 ms762 ms
TTFT333 ms762 ms
Load time4.5 sN/A
Memory usage8.6 GB0.1 GB
Memory %7%0%

HW Fit Score Breakdown

gemma3n:latest

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

falcon-h1-tiny-90m-inst…

Speed
50/50
TTFT
20/20
Memory
29/30

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

falcon-h1-tiny-90m-inst…

Reasoning
5/20
Coding
0/20
Instruction
7/20
Structured
3/15
Math
2/15
Multilingual
2/10
Reasoning: Weak Coding: Poor Instruction Following: Weak 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