gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
gemma-4-26b-a4b-it-qat
LM-STUDIO GGUFgemma4 · 26B · Q4_K_XL
Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
83 vs 88
Hardware Fit
64 vs 77
Quality Score
91 vs 93
Hardware
gpt-oss:120b gemma-4-26b-a4b-it…
MachineNVIDIA NVIDIA_DGX_SparkASUS
CPUCortex-X925AMD Ryzen 7 7800X3D 8-Core Processor
Cores2016
RAM122 GB31 GB
GPUDevice 2e12NVIDIA GeForce RTX 4090, Raphael
OSUbuntu 24.04.5 LTScachyos rolling
Archarm64x64
Power Modeperformanceperformance
Performance
gpt-oss:120b gemma-4-26b-a4b-it…
Tokens/sec28.6169.6
First chunk422 ms9 ms
TTFT2.5 s108 ms
Load time9.9 sN/A
Memory usage60.1 GB26.0 GB
Memory %49%85%
HW Fit Score Breakdown
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
gemma-4-26b-a4b-it-qat
Speed
50/50
TTFT
20/20
Memory
7/30
Quality
gpt-oss:120b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma-4-26b-a4b-it-qat
Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest