DeepSeek-V4-Flash
DeepSeek-V4-Flash is an open-weights language model from DeepSeek, released April 24, 2026. It has 304B parameters (mixture-of-experts, 34B active). The context window is 1M tokens. On the Epoch Capabilities Index it scores 146.8, rank 86 of 256 rated models. API price: $0.15 input / $0.6 output per million tokens.
We present a preview version of DeepSeek-V4 series, including two strong Mixture-ofExperts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens.
Check it against your own PC →
Can you run DeepSeek-V4-Flash 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: huihui-ai/Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF · unsloth/DeepSeek-V4-Flash-0731-GGUF · lmstudio-community/DeepSeek-V4-Flash-0731-GGUF · KeinNiemand/DeepSeek-V4-Flash-0731-IK_GGUF · Lucebox/DeepSeek-V4-Flash-0731-ROCmFP3 · AtomicChat/DeepSeek-V4-Flash-0731-GGUF
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| SimpleBench | 35.6% |
Links
Announcement · Hugging Face: deepseek-ai/DeepSeek-V4-Flash-0731 · Epoch AI benchmarks
Models with a similar score
Inkling-Small · GLM-5.1 · DeepSeek-V4-Pro · GPT-5 · Grok 4.3 Beta · Qwen 3.6 Max (Preview) · GPT-5.4 Mini · Qwen 3.6 Plus
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 Flash DSpark · DeepSeek-V4-Pro