hf.co/TheDrummer/Cydonia-24B-v4.3-GGUF:Q4_K_M
OLLAMA GGUFllama · 23.6B · unknown
Oct 2, 2026 · Cortex-X925
llama3.3:70b
OLLAMA GGUFllama · 70.6B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
30 vs 73
Hardware Fit
48 vs 51
Quality Score
22 vs 83
Hardware
hf.co/TheDrummer/C… llama3.3:70b
MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA_DGX_Spark
CPUCortex-X925Cortex-X925
Cores2020
RAM122 GB122 GB
GPUDevice 2e12Device 2e12
OSUbuntu 24.04.5 LTSUbuntu 24.04.4 LTS
Archarm64arm64
Power Modeperformanceperformance
Performance
hf.co/TheDrummer/C… llama3.3:70b
Tokens/sec14.44.6
First chunk5450 ms560 ms
TTFT5.5 s560 ms
Load time22.7 s13.8 s
Memory usage18.5 GB49.5 GB
Memory %15%41%
HW Fit Score Breakdown
hf.co/TheDrummer/Cydoni…
Speed
14/50
TTFT
4/20
Memory
30/30
llama3.3:70b
Speed
4/50
TTFT
20/20
Memory
27/30
Quality
hf.co/TheDrummer/Cydoni…
Reasoning
16/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
6/15
Multilingual
0/10
Reasoning: Strong Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Poor
llama3.3:70b
Reasoning
17/20
Coding
18/20
Instruction
12/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest