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

google/gemma-3-27b

LM-STUDIO MLX

gemma3 · 27B · 4bit

Not Rec.

Mar 19, 2026 · Apple M4

Global Score
66 vs 71
Hardware Fit
51 vs 35
Quality Score
73 vs 86

Hardware

ornith-1.5-9b_hybr… google/gemma-3-27b
MachineMicro-Star International Co., Ltd. MS-7C37Mac mini
CPUAMD Ryzen 9 3900X 12-Core ProcessorApple M4
Cores2410
RAM128 GB24 GB
GPUIntel(R) Arc(TM) Pro B70 GraphicsApple M4
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

ornith-1.5-9b_hybr… google/gemma-3-27b
Tokens/sec5.45.9
First chunk39 ms19 ms
TTFT940 ms1.8 s
Load timeN/AN/A
Memory usage10.7 GB22.0 GB
Memory %8%92%

HW Fit Score Breakdown

ornith-1.5-9b_hybrid-im…

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

google/gemma-3-27b

Speed
12/50
TTFT
19/20
Memory
4/30

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

google/gemma-3-27b

Reasoning
16/20
Coding
18/20
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

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