bartowski / text-generation updated 1 month ago

DeepSeek-V4-Flash-GGUF

No other sizes can be provided unfortunately as MXFP4 does not quantize properly.

Params
Context
Downloads 30d
245 K
Likes
33
Commercial use: allowed mit Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 10 days
245 K245 K
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.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
DeepSeek-V4-Flash-MXFP4-00002-of-00004.gguf GGUF 39.6 GB 44.1 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
~ · ollama · GGUF
$ ollama run deepseek-v4-flash-gguf

# pin the quantization explicitly
$ ollama run deepseek-v4-flash-gguf-gguf
est. VRAM 44.1 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
mit
First seen on the Hub
2026-06-29
Base model
DeepSeek-V4-Flash
Training datasets
undisclosed
Added to our catalog
2026-07-28

Family

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

Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.