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

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

Global Score
66 vs 66
Hardware Fit
51 vs 40
Quality Score
73 vs 77

Hardware

ornith-1.5-9b_hybr… gemma4:31b
MachineMicro-Star International Co., Ltd. MS-7C37ASUSTeK COMPUTER INC. GX10
CPUAMD Ryzen 9 3900X 12-Core ProcessorCortex-X925
Cores2420
RAM128 GB122 GB
GPUIntel(R) Arc(TM) Pro B70 GraphicsDevice 2e12
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

ornith-1.5-9b_hybr… gemma4:31b
Tokens/sec5.410.7
First chunk39 ms983 ms
TTFT940 ms20.3 s
Load timeN/A8.8 s
Memory usage10.7 GB21.4 GB
Memory %8%18%

HW Fit Score Breakdown

ornith-1.5-9b_hybrid-im…

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

gemma4:31b

Speed
10/50
TTFT
0/20
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

gemma4:31b

Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View ornith-1.5-9b_hybr… details | View gemma4:31b 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