Back to leaderboard

swift-1.5-iq2_xs

LM-STUDIO UNKNOWN
Excellent

Nov 14, 2026 · AMD Ryzen 5 5600X 6-Core Processor

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Good

Aug 19, 2026 · Intel Core™ Ultra X7 358H

Global Score
96 vs 79
Hardware Fit
94 vs 59
Quality Score
97 vs 88

Hardware

swift-1.5-iq2_xs GPT-20B:20b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROGMKtec NucBox EVO-T2S
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Core™ Ultra X7 358H
Cores1216
RAM47 GB64 GB
GPUAD106 [GeForce RTX 4060 Ti]Intel(R) Arc(TM) B390 GPU
OSArch LinuxMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

swift-1.5-iq2_xs GPT-20B:20b
Tokens/sec60.019.3
First chunk2 ms2004 ms
TTFT2.6 s10.4 s
Load timeN/A10.4 s
Memory usage0.9 GB12.9 GB
Memory %2%20%

HW Fit Score Breakdown

swift-1.5-iq2_xs

Speed
50/50
TTFT
14/20
Memory
30/30

GPT-20B:20b

Speed
26/50
TTFT
3/20
Memory
30/30

Quality

swift-1.5-iq2_xs

Reasoning
20/20
Coding
19/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

GPT-20B:20b

Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View swift-1.5-iq2_xs details | View GPT-20B:20b 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