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

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

Global Score
85 vs 81
Hardware Fit
80 vs 100
Quality Score
87 vs 73

Hardware

gemma4:12b-fast gemma3n:latest
MachineASUSSupermicro AS -2015HS-TNR
CPUIntel Gen Intel® Core™ i7-12700AMD EPYC 9654P 96-Core Processor
Cores2064
RAM30 GB128 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSUbuntu 26.04.1 LTSUbuntu 24.04.3 LTS
Archx64x64
Power Modelow-powerperformance

Performance

gemma4:12b-fast gemma3n:latest
Tokens/sec75.9108.7
First chunk169 ms333 ms
TTFT30.0 s333 ms
Load time8.4 s4.5 s
Memory usage1.3 GB8.6 GB
Memory %5%7%

HW Fit Score Breakdown

gemma4:12b-fast

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

gemma3n:latest

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

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

gemma3n:latest

Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View gemma4:12b-fast details | View gemma3n:latest 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