Back to leaderboard

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

qwen3-coder:latest

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

Global Score
87 vs 76
Hardware Fit
81 vs 51
Quality Score
90 vs 87

Hardware

GPT-20B:20b qwen3-coder:latest
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxDell Inc. Inspiron 15 3530
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorIntel Gen Intel® Core™ i7-1355U
Cores3212
RAM31 GB31 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPURaptor Lake-P [Iris Xe Graphics]
OSMicrosoft Windows 11 Home 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

GPT-20B:20b qwen3-coder:latest
Tokens/sec36.97.6
First chunk902 ms2037 ms
TTFT4.2 s2.0 s
Load time19.5 s8.7 s
Memory usage13.1 GB18.9 GB
Memory %42%61%

HW Fit Score Breakdown

GPT-20B:20b

Speed
47/50
TTFT
7/20
Memory
27/30

qwen3-coder:latest

Speed
13/50
TTFT
18/20
Memory
20/30

Quality

GPT-20B:20b

Reasoning
19/20
Coding
17/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen3-coder:latest

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View GPT-20B:20b details | View qwen3-coder:latest 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