llama4:scout

llama4 · 108.6B · Q4_K_M

NVIDIA NVIDIA_DGX_Spark (Cortex-X925)

122 GB · Ubuntu 24.04.5 LTS

Tested on October 3, 2026 · Submitted by Tram

Top 37% Compare

Global Score

81 /100

Excellent

Hardware Fit

64/100

Quality

88/100

Get this model

🦙

Ollama

ollama pull llama4:scout

View on Ollama Library

ollama.com/library/llama4

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: 19.6
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: 677 ms
Time to first token How fast the model starts responding — lower is better: 677 ms
Load time Time to load the model into memory before inference: 13.1 s
Memory usage RAM consumed during inference — percentage of total system memory: 63.4 GB (52%)
Total tokens Total number of tokens generated across all benchmark prompts: 2788

Score breakdown

Speed

20/50

Time to first token

20/20

Memory

24/30

Quality

Reasoning

17/20

Coding

19/20

Instruction following

16/20

Structured output

13/15

Math

13/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.35.0
Model format: GGUF
Hardware profile: HIGH-END
Result hash: db3c04a46ba575b8b8ef2758dee00e1d31b3b31e178824aa581efc23301b1bf8

Interpretation

Hardware fit: 64/100. Overall suitability: EXCELLENT (Global 81/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

Thermal: nominal CPU load: avg 13% (peak 15%)

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