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

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
66 vs 68
Hardware Fit
99 vs 93
Quality Score
52 vs 57

Hardware

granite3.1-moe:3b google/gemma-4-e4b
MachineDell Inc. Inspiron 15 3530LENOVO 82JQ
CPUIntel Gen Intel® Core™ i7-1355UAMD Ryzen 7 5800H
Cores1216
RAM31 GB16 GB
GPURaptor Lake-P [Iris Xe Graphics]NVIDIA GeForce RTX 3060 Laptop GPU
OScachyos rollingMicrosoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modelow-powerbalanced

Performance

granite3.1-moe:3b google/gemma-4-e4b
Tokens/sec27.226.2
First chunk527 ms17 ms
TTFT527 ms572 ms
Load time1.9 sN/A
Memory usage2.9 GB6.5 GB
Memory %9%41%

HW Fit Score Breakdown

granite3.1-moe:3b

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

google/gemma-4-e4b

Speed
46/50
TTFT
20/20
Memory
27/30

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

google/gemma-4-e4b

Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor
View granite3.1-moe:3b details | View google/gemma-4-e4b details

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