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

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor

Global Score
85 vs 82
Hardware Fit
80 vs 90
Quality Score
87 vs 79

Hardware

gemma4:12b-fast qwen3:14b
MachineASUSMicro-Star International Co., Ltd. MS-7C37
CPUIntel Gen Intel® Core™ i7-12700AMD Ryzen 9 3900X 12-Core Processor
Cores2024
RAM30 GB64 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060GameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 专业版 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

gemma4:12b-fast qwen3:14b
Tokens/sec75.974.4
First chunk169 ms324 ms
TTFT30.0 s2.6 s
Load time8.4 s5.1 s
Memory usage1.3 GB9.0 GB
Memory %5%14%

HW Fit Score Breakdown

gemma4:12b-fast

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

qwen3:14b

Speed
50/50
TTFT
10/20
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

qwen3:14b

Reasoning
18/20
Coding
11/20
Instruction
17/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View gemma4:12b-fast details | View qwen3:14b 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