Back to leaderboard

ornith-1.5-9b_hybrid-imatrix

LM-STUDIO GGUF

qwen35 · F16

Not Rec.

Aug 23, 2026 · AMD Ryzen 9 3900X 12-Core Processor

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Good

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

Global Score
66 vs 79
Hardware Fit
51 vs 59
Quality Score
73 vs 88

Hardware

ornith-1.5-9b_hybr… GPT-20B:20b
MachineMicro-Star International Co., Ltd. MS-7C37GMKtec NucBox EVO-T2S
CPUAMD Ryzen 9 3900X 12-Core ProcessorIntel Core™ Ultra X7 358H
Cores2416
RAM128 GB64 GB
GPUIntel(R) Arc(TM) Pro B70 GraphicsIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

ornith-1.5-9b_hybr… GPT-20B:20b
Tokens/sec5.419.3
First chunk39 ms2004 ms
TTFT940 ms10.4 s
Load timeN/A10.4 s
Memory usage10.7 GB12.9 GB
Memory %8%20%

HW Fit Score Breakdown

ornith-1.5-9b_hybrid-im…

Speed
5/50
TTFT
16/20
Memory
30/30

GPT-20B:20b

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

Quality

ornith-1.5-9b_hybrid-im…

Reasoning
14/20
Coding
14/20
Instruction
11/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate 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 ornith-1.5-9b_hybr… 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