Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

granite3.1-moe:3b

OLLAMA GGUF

granitemoe · 3.3B · Q4_K_M

Good

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

Global Score
83 vs 66
Hardware Fit
96 vs 99
Quality Score
78 vs 52

Hardware

google/gemma-4-e4b granite3.1-moe:3b
MachineASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PHDell Inc. Inspiron 15 3530
CPUAMD Ryzen 9 8940HXIntel Gen Intel® Core™ i7-1355U
Cores3212
RAM15 GB31 GB
GPUNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610MRaptor Lake-P [Iris Xe Graphics]
OSMicrosoft Windows 11 Home Single Language 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

google/gemma-4-e4b granite3.1-moe:3b
Tokens/sec35.927.2
First chunk9 ms527 ms
TTFT182 ms527 ms
Load timeN/A1.9 s
Memory usage6.5 GB2.9 GB
Memory %43%9%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
49/50
TTFT
20/20
Memory
27/30

granite3.1-moe:3b

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

Quality

google/gemma-4-e4b

Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

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

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