DeepSeek V4 Flash on Dual DGX Spark: VRAM, speed and fit
DeepSeek V4 Flash at FP4 + FP8 runs on the DGX Spark 128 GB with 1M of context at about 9.9 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on DGX Spark 128 GB · FP4 + FP8 · Ollama / LM Studio · Chat
- GPU memory
- 178 GB
- of 256 GB
- Context
- 1M
- auto
- Speed
- 9.9 tok/s
- 7.4 when full
- First reply
- 2.0 s
- 2K prompt
Where the memory goes
- Model
- 155 GB
- Context
- 6.1 GB
- Overhead
- 1.1 GB
- OS
- 15.4 GB
- Free
- 78.1 GB
- Memory
- 178 GB of 256 GB
- Context
- 1M tokens · auto
- Speed
- 9.9 tok/s · 7.4 when full
- First reply
- 2.0 s for a 2K prompt
- Running cost
- $3.15/mo at home · $287/mo on a cloud 4× A40
Validation: Validated with conditions
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 241 GB usable | 163 GB needed | Pass |
| Headroom | 5% free | 78.1 GB free (32%) | Pass |
| Context for chat | 16K or more | 1M | Pass |
| Writing speed | 15 tok/s or more | 9.9 tok/s | Check |
| First reply | under 3 s, 2K prompt | 2.0 s | Pass |
Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.
The setup
- Model
- DeepSeek V4 Flash
- Parameters
- 284B, 13B active
- Precision
- FP4 + FP8
- Context
- 1M, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- DGX Spark 128 GB
- GPU can use
- 241 GB of 256 GB
Running cost
- At home
- $3.15/mo
- 144 W at the wall
- Renting instead
- $287/mo
- 4× A40 at $2.36/h
4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.
How to run it
- llama.cpp
llama-server -hf unsloth/DeepSeek-V4-Flash-0731-GGUF- vLLM
vllm serve deepseek-ai/DeepSeek-V4-Flash-0731- MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-V4-Flash-0731-2.4bit-mixed
DeepSeek V4 Flash on similar machines
- Ryzen AI Max+ 395 64 GBToo big
- Ryzen AI Max+ 395 128 GBJust misses
- RTX SparkRuns
- DGX SparkRuns
- DGX Station GB300Runs
- 2× RTX PRO 6000 BlackwellRuns
- 4× RTX PRO 6000 BlackwellRuns
- 8× RTX PRO 6000 BlackwellRuns
All machines: DeepSeek V4 Flash VRAM requirements. Everything that runs here: what can the Dual DGX Spark run?
Other models that run on Dual DGX Spark
Questions
Can DeepSeek V4 Flash run on Dual DGX Spark?
DeepSeek V4 Flash at FP4 + FP8 runs on the DGX Spark 128 GB with 1M of context at about 9.9 tokens a second.
Report VR-08WTSSS, calculated Nov 22, 2026 from published specs, not benchmarked.