granite3.1-moe:3b
OLLAMA GGUFgranitemoe · 3.3B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
unsloth/gemma-4-e2b-it@q8_0
LM-STUDIO GGUFgemma4 · Q8_0
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
66 vs 75
Hardware Fit
99 vs 74
Quality Score
52 vs 76
Hardware
granite3.1-moe:3b unsloth/gemma-4-e2…
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 unsloth/gemma-4-e2…
Tokens/sec27.213.0
First chunk527 ms62 ms
TTFT527 ms1.5 s
Load time1.9 s7.8 s
Memory usage2.9 GB0.0 GB
Memory %9%0%
HW Fit Score Breakdown
granite3.1-moe:3b
Speed
49/50
TTFT
20/20
Memory
30/30
unsloth/gemma-4-e2b-it@…
Speed
24/50
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
unsloth/gemma-4-e2b-it@…
Reasoning
11/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest