Back to leaderboard

gemma4:12b-fast

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Not Rec.

Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
85 vs 68
Hardware Fit
80 vs 93
Quality Score
87 vs 57

Hardware

gemma4:12b-fast google/gemma-4-e4b
MachineASUSLENOVO 82JQ
CPUIntel Gen Intel® Core™ i7-12700AMD Ryzen 7 5800H
Cores2016
RAM30 GB16 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060NVIDIA GeForce RTX 3060 Laptop GPU
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modelow-powerbalanced

Performance

gemma4:12b-fast google/gemma-4-e4b
Tokens/sec75.926.2
First chunk169 ms17 ms
TTFT30.0 s572 ms
Load time8.4 sN/A
Memory usage1.3 GB6.5 GB
Memory %5%41%

HW Fit Score Breakdown

gemma4:12b-fast

Speed
50/50
TTFT
0/20
Memory
30/30

google/gemma-4-e4b

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

Quality

gemma4:12b-fast

Reasoning
18/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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 gemma4:12b-fast 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