gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Sep 15, 2026 · Intel Core™ i5-14400F
llama4:scout
OLLAMA GGUFllama4 · 108.6B · Q4_K_M
Oct 3, 2026 · Cortex-X925
Global Score
94 vs 81
Hardware Fit
97 vs 64
Quality Score
93 vs 88
Hardware
gpt-oss:20b llama4:scout
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4NVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i5-14400FCortex-X925
Cores1620
RAM32 GB122 GB
GPUNVIDIA GeForce RTX 5060 TiDevice 2e12
OSMicrosoft Windows 11 Professionnel 10.0.26200Ubuntu 24.04.5 LTS
Archx64arm64
Power Modebalancedperformance
Performance
gpt-oss:20b llama4:scout
Tokens/sec80.419.6
First chunk139 ms677 ms
TTFT1.6 s677 ms
Load time11.6 s13.1 s
Memory usage11.9 GB63.4 GB
Memory %37%52%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
19/20
Memory
28/30
llama4:scout
Speed
20/50
TTFT
20/20
Memory
24/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
llama4:scout
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
13/15
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