Back to leaderboard

gemma-4-31b-it-qat

LM-STUDIO GGUF

gemma4 · 31B · Q4_K_XL

Excellent

Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

Global Score
91 vs 83
Hardware Fit
89 vs 96
Quality Score
92 vs 78

Hardware

gemma-4-31b-it-qat google/gemma-4-e4b
MachineASUSASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD Ryzen 9 8940HX
Cores1632
RAM31 GB15 GB
GPUNVIDIA GeForce RTX 4090, RaphaelNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OScachyos rollingMicrosoft Windows 11 Home Single Language 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

gemma-4-31b-it-qat google/gemma-4-e4b
Tokens/sec40.235.9
First chunk3 ms9 ms
TTFT302 ms182 ms
Load timeN/AN/A
Memory usage18.8 GB6.5 GB
Memory %62%43%

HW Fit Score Breakdown

gemma-4-31b-it-qat

Speed
50/50
TTFT
20/20
Memory
19/30

google/gemma-4-e4b

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

Quality

gemma-4-31b-it-qat

Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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
View gemma-4-31b-it-qat 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