ornith-1.5-9b_hybrid-imatrix

qwen35 · F16

Micro-Star International Co., Ltd. MS-7C37 (AMD Ryzen 9 3900X 12-Core Processor)

128 GB · Microsoft Windows 11 Pro 10.0.26200

Tested on August 23, 2026 · Submitted by JohnnyMoon

Top 69% Compare

Global Score

66 /100

Not Rec.

Hardware Fit

51/100

Quality

73/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: Micro-Star International Co., Ltd. MS-7C37
CPU: AMD Ryzen 9 3900X 12-Core Processor
Cores: 24 total (24 perf)
Frequency: 3.8 GHz
RAM: 128 GB DDR4
GPU: Intel(R) Arc(TM) Pro B70 Graphics
OS: Microsoft Windows 11 Pro 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 5.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.3
First chunk latency Delay before the first streamed chunk arrives from runtime: 39 ms
Time to first token How fast the model starts responding — lower is better: 940 ms
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 10.7 GB (8%)
Total tokens Total number of tokens generated across all benchmark prompts: 1273

Score breakdown

Speed

5/50

Time to first token

16/20

Memory

30/30

Quality

Reasoning

14/20

Coding

14/20

Instruction following

11/20

Structured output

15/15

Math

9/15

Multilingual

10/10

Category levels

Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: LM Studio
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 0d62c94d768feea61df171f9c0c332adaba1d0111eed9f5b0eb8e3ac915b85b7

Interpretation

Hardware fit: 51/100. Overall suitability: NOT RECOMMENDED (Global 66/100). Category profile: Reasoning: Adequate, Coding: Adequate, Instruction Following: Adequate, Structured Output: Strong, Math: Adequate, Multilingual: Strong.

Warnings

Model memory footprint is estimated via LM Studio CLI rather than measured from a fresh load.
High CPU load during inference (avg 91%). System may feel unresponsive — GPU-accelerated runtimes (MLX) can reduce CPU pressure.

Disqualifiers

Token speed too low: 5.4 tok/s (minimum: 8 tok/s for HIGH-END profile)

Bench Environment

Swap delta: +0.1 GB CPU load: avg 91% (peak 99%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest