granite3.1-moe:3b

OLLAMA GGUF

granitemoe · 3.3B · Q4_K_M

Good

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

lmstudio-community/gemma-4-e4b-it-qat

LM-STUDIO GGUF

gemma4 · Q4_0

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score

66 vs 77

Hardware Fit

99 vs 68

Quality Score

52 vs 81

Hardware

granite3.1-moe:3b lmstudio-community…

MachineDell Inc. Inspiron 15 3530Docker Container

CPUIntel Gen Intel® Core™ i7-1355UIntel Gen Intel® Core™ i9-11900H

Cores1216

RAM31 GB15 GB

GPURaptor Lake-P [Iris Xe Graphics]TigerLake-H GT1 [UHD Graphics]

OScachyos rollingUbuntu 26.04 LTS

Archx64x64

Power Modelow-powerperformance

Performance

granite3.1-moe:3b lmstudio-community…

Tokens/sec27.211.4

First chunk527 ms28 ms

TTFT527 ms2.2 s

Load time1.9 s6.8 s

Memory usage2.9 GB0.6 GB

Memory %9%4%

HW Fit Score Breakdown

granite3.1-moe:3b

Speed

49/50

TTFT

20/20

Memory

30/30

lmstudio-community/gemm…

Speed

21/50

TTFT

17/20

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

lmstudio-community/gemm…

Reasoning

14/20

Coding

19/20

Instruction

15/20

Structured

15/15

Math

8/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

View granite3.1-moe:3b details | View lmstudio-community… 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