antirez / text-generation updated 2 days ago

deepseek-v4-gguf

This quants are specific for the DS4 inference engine. They may work with other inference engines or not (they should, but not the MTP model which requires a specific loader).

Params
Context
Downloads 30d
875 K
Likes
423
Commercial use: allowed mit Not gated GGUF 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
875 K654 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-MTP-Q4K-Q8_0-F32.gguf Q8_0 3.8 GB 4.7 GB ✅ Runs comfortably
DeepSeek-V4-Pro-Q4K-Layers00-30.gguf GGUF 457.5 GB 503.8 GB ❌ Won’t fit
DeepSeek-V4-Pro-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-Instruct-imatrix.gguf Q8 464.6 GB 511.6 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-gguf

# pin the quantization explicitly
$ ollama run deepseek-v4-gguf-gguf
est. VRAM 503.8 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
mit
First seen on the Hub
2026-04-26
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.