DeepSeek V4 Flash DSpark
DeepSeek V4 Flash DSpark is an open-weights language model from DeepSeek, released June 27, 2026. It has 304B parameters (mixture-of-experts, 34B active). The context window is 1M tokens.
Check it against your own PC →
Can you run DeepSeek V4 Flash DSpark locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Too large | – | – | – | – |
Ready-made quantizations on Hugging Face: alessandrobologna/DeepSeek-V4-Flash-DSpark-Drafter-GGUF · sakamakismile/DeepSeek-V4-Flash-DSpark-support-ds4-GGUF · yailabs/DeepSeek-V4-Flash-GGUF · drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored · anemll/DeepSeek-V4-Flash-NVFP4-TP2-W4A4-v1 · drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored-v1.1-alpha-Mida-Brikie
Benchmark results
Epoch AI has not published results for DeepSeek V4 Flash DSpark yet. New models are usually evaluated within days to weeks.
Links
Hugging Face: deepseek-ai/DeepSeek-V4-Flash-DSpark
More from DeepSeek
DeepSeek V4.1 Flash 1017 · DeepSeek V4 Flash Vision Exp · DeepSeek V4.1 Flash · DeepSeek V4 Pro 0813 · DeepSeek V4 Flash 0731 · DeepSeek V4 Pro DSpark · DeepSeek-V4-Pro · DeepSeek-V4-Flash