qwen2.5:14b

OLLAMA GGUF

qwen2 · 14.8B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

Global Score

90 vs 66

Hardware Fit

100 vs 40

Quality Score

85 vs 77

Hardware

qwen2.5:14b gemma4:31b

MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4ASUSTeK COMPUTER INC. GX10

CPUIntel Core™ i5-14400FCortex-X925

Cores1620

RAM32 GB122 GB

GPUNVIDIA GeForce RTX 5060 TiDevice 2e12

OSMicrosoft Windows 11 Professionnel 10.0.26200Ubuntu 24.04.4 LTS

Archx64arm64

Power Modebalancedperformance

Performance

qwen2.5:14b gemma4:31b

Tokens/sec37.810.7

First chunk74 ms983 ms

TTFT74 ms20.3 s

Load time6.2 s8.8 s

Memory usage8.8 GB21.4 GB

Memory %28%18%

HW Fit Score Breakdown

qwen2.5:14b

Speed

50/50

TTFT

20/20

Memory

30/30

gemma4:31b

Speed

10/50

TTFT

0/20

Memory

30/30

Quality

qwen2.5:14b

Reasoning

17/20

Coding

18/20

Instruction

14/20

Structured

15/15

Math

11/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

gemma4:31b

Reasoning

14/20

Coding

17/20

Instruction

13/20

Structured

14/15

Math

10/15

Multilingual

9/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

View qwen2.5:14b details | View gemma4:31b 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