Back to leaderboard

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_XL

Excellent

Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
93 vs 90
Hardware Fit
91 vs 82
Quality Score
94 vs 93

Hardware

GPT-20B:20b gemma-4-26b-a4b-it…
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLASUS
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )AMD Ryzen 7 7800X3D 8-Core Processor
Cores2016
RAM55 GB31 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUNVIDIA GeForce RTX 4090, Raphael
OSMicrosoft Windows 11 Pro 10.0.28000cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

GPT-20B:20b gemma-4-26b-a4b-it…
Tokens/sec57.8156.5
First chunk203 ms10 ms
TTFT3.0 s124 ms
Load time19.2 sN/A
Memory usage12.0 GB23.3 GB
Memory %22%76%

HW Fit Score Breakdown

GPT-20B:20b

Speed
50/50
TTFT
11/20
Memory
30/30

gemma-4-26b-a4b-it-qat

Speed
50/50
TTFT
20/20
Memory
12/30

Quality

GPT-20B:20b

Reasoning
19/20
Coding
17/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest