Back to leaderboard

granite3.1-moe:3b

OLLAMA GGUF

granitemoe · 3.3B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

Global Score
66 vs 81
Hardware Fit
99 vs 100
Quality Score
52 vs 73

Hardware

granite3.1-moe:3b gemma3n:latest
MachineDell Inc. Inspiron 15 3530Supermicro AS -2015HS-TNR
CPUIntel Gen Intel® Core™ i7-1355UAMD EPYC 9654P 96-Core Processor
Cores1264
RAM31 GB128 GB
GPURaptor Lake-P [Iris Xe Graphics]GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OScachyos rollingUbuntu 24.04.3 LTS
Archx64x64
Power Modelow-powerperformance

Performance

granite3.1-moe:3b gemma3n:latest
Tokens/sec27.2108.7
First chunk527 ms333 ms
TTFT527 ms333 ms
Load time1.9 s4.5 s
Memory usage2.9 GB8.6 GB
Memory %9%7%

HW Fit Score Breakdown

granite3.1-moe:3b

Speed
49/50
TTFT
20/20
Memory
30/30

gemma3n:latest

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

Quality

granite3.1-moe:3b

Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
5/15
Multilingual
6/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate

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