GPT-OSS-120B:120B

OLLAMA GGUF

gptoss · 116.8B · MXFP4

Not Rec.

Aug 18, 2026 · Intel Core™ Ultra X7 358H

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score

67 vs 62

Hardware Fit

21 vs 77

Quality Score

87 vs 55

Hardware

GPT-OSS-120B:120B google/gemma-4-e4b

MachineGMKtec NucBox EVO-T2SLENOVO 82JQ

CPUIntel Core™ Ultra X7 358HAMD Ryzen 7 5800H

Cores1616

RAM64 GB16 GB

GPUIntel(R) Arc(TM) B390 GPUNVIDIA GeForce RTX 3060 Laptop GPU

OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 家庭版中文版 10.0.26100

Archx64x64

Power Modebalancedbalanced

Performance

GPT-OSS-120B:120B google/gemma-4-e4b

Tokens/sec11.727.6

First chunk4289 ms23 ms

TTFT9.2 s480 ms

Load time84.1 sN/A

Memory usage61.0 GB13.2 GB

Memory %96%83%

HW Fit Score Breakdown

GPT-OSS-120B:120B

Speed

15/50

TTFT

4/20

Memory

2/30

google/gemma-4-e4b

Speed

48/50

TTFT

20/20

Memory

9/30

Quality

GPT-OSS-120B:120B

Reasoning

18/20

Coding

19/20

Instruction

10/20

Structured

15/15

Math

15/15

Multilingual

10/10

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

google/gemma-4-e4b

Reasoning

18/20

Coding

17/20

Instruction

5/20

Structured

3/15

Math

11/15

Multilingual

1/10

Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor

View GPT-OSS-120B:120B 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