deepseek-coder-v2:16b

deepseek2 · 15.7B · Q4_0

NVIDIA NVIDIA_DGX_Spark (Cortex-X925)

122 GB · Ubuntu 24.04.4 LTS

Tested on June 26, 2026

Top 20% Compare

Global Score

82 /100

Excellent

Hardware Fit

100/100

Quality

74/100

Get this model

🦙

Ollama

ollama pull deepseek-coder-v2:16b

View on Ollama Library

ollama.com/library/deepseek-coder-v2

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 24.04.4 LTS
Arch: arm64
Power Mode: performance

Performance

Tokens/sec Tokens generated per second — higher is better: 117.2
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.2
First chunk latency Delay before the first streamed chunk arrives from runtime: 275 ms
Time to first token How fast the model starts responding — lower is better: 275 ms
Load time Time to load the model into memory before inference: 8.9 s
Memory usage RAM consumed during inference — percentage of total system memory: 17.9 GB (15%)
Total tokens Total number of tokens generated across all benchmark prompts: 1093

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

8/20

Coding

19/20

Instruction following

13/20

Structured output

12/15

Math

14/15

Multilingual

8/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.30.10
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 2ee87b25335a111e31f1bfd63a0592ff997fd9f0ed4858f6147ece7695654374

Interpretation

Hardware fit: 100/100. Overall suitability: EXCELLENT (Global 82/100). Category profile: Reasoning: Weak, Coding: Strong, Instruction Following: Adequate, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

Thermal: nominal CPU load: avg 15% (peak 33%)

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