deepseek-ai / text-generation updated 1 month ago

DeepSeek-V4-Flash

Name: DeepSeek-V4-Flash
Author: deepseek-ai

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (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.

Params

158.1 B

Context

1,048,576

Downloads 30d

2.7 M

Likes

2,031

Commercial use: allowed mit Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

3.1 M2.7 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	i8	159.6 GB	199.8 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 1024K ctx	159.6 GB	3,211.0 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/deepseek-v4-flash
{
  "hf_id": "deepseek-ai/DeepSeek-V4-Flash",
  "params_b": 158.07,
  "context_length": 1048576,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 2737621,
  "vram_estimates": [
    { "quant": "i8", "gb": 199.8 }
  ],
  "updated_at": "2026-07-28T17:07:23Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: DeepseekV4ForCausalLM
Parameters: 158.1 B
Tensor type: I8
Context length: 1,048,576
Vocabulary: 129,280
Layers / heads: 43 / 64
Licence: mit
First seen on the Hub: 2026-04-22
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative DeepSeek-V4-Flash-NVFP4 nvidia 1.1 M Derivative deepseek-v4-gguf antirez 875 K Derivative DeepSeek-V4-Flash-GGUF bartowski 245 K

Compare with

gpt-oss-120b 4.2 M NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 2.8 M Qwen3-Coder-Next-FP8 2.2 M Qwen-72B 2.2 M GLM-5.2-NVFP4 1.8 M DeepSeek-V4-Flash-NVFP4 1.1 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB