hf.co/TheDrummer/Cydonia-24B-v4.3-GGUF:Q4_K_M

llama · 23.6B · unknown

NVIDIA NVIDIA_DGX_Spark (Cortex-X925)

122 GB · Ubuntu 24.04.5 LTS

Tested on October 2, 2026 · Submitted by Tram

Top 97% Compare

Global Score

30 /100

Not Rec.

Hardware Fit

48/100

Quality

22/100

Get this model

🦙

Ollama

ollama pull hf.co/TheDrummer/Cydonia-24B-v4.3-GGUF:Q4_K_M

View on Ollama Library

ollama.com/library/hf.co/TheDrummer/Cydonia-24B-v4.3-GGUF

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: NVIDIA NVIDIA_DGX_Spark
CPU: Cortex-X925
Cores: 20 total (20 perf)
Frequency: 3.35 GHz
RAM: 122 GB
GPU: Device 2e12
OS: Ubuntu 24.04.5 LTS
Arch: arm64
Power Mode: performance

Performance

Tokens/sec Tokens generated per second — higher is better: 14.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
First chunk latency Delay before the first streamed chunk arrives from runtime: 5.5 s
Time to first token How fast the model starts responding — lower is better: 5.5 s
Load time Time to load the model into memory before inference: 22.7 s
Memory usage RAM consumed during inference — percentage of total system memory: 18.5 GB (15%)
Total tokens Total number of tokens generated across all benchmark prompts: 1032

Score breakdown

Speed

14/50

Time to first token

4/20

Memory

30/30

Quality

Reasoning

16/20

Coding

0/20

Instruction following

0/20

Structured output

0/15

Math

6/15

Multilingual

0/10

Category levels

Reasoning: Strong Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Poor

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.34.0
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 48c70280f32252d4dd867aa9b7a0066a52d66e51a89abf32bdaebb6f44513dfb

Interpretation

Hardware fit: 48/100. Overall suitability: NOT RECOMMENDED (Global 30/100). Category profile: Reasoning: Strong, Coding: Poor, Instruction Following: Poor, Structured Output: Poor, Math: Weak, Multilingual: Poor.

Bench Environment

Thermal: nominal CPU load: avg 11% (peak 13%)

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