Model reference · open weights

deepseek

deepseek is an open-weight language model from antirez, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

LLMs antirez 1 variants 2.1M downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What deepseek is

DeepSeek V4 Flash — GGUF for ds4 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). https://github.com/antirez/ds4 Files Use q2 on 128 GB Mac machines, q4 on machines with ≥ 256 GB RAM, pair either with MTP for optional speculative decoding. Quantization recipe The filename is the spec. In detail, for the q2 file: For the q4 file, only the three routed-expert classes change to Q4K. Everything else is byte-for-byte identical to the q2 recipe. The motivation behind the asymmetry: the routed experts are the majority of the parameter count but each individual expert handles only a fraction of tokens, so aggressive quantization on them costs less in average quality than the same treatment of router, projections, or shared experts. Keeping the decision-making components at Q80 preserves model behavior; crushing the experts buys the size. Usage The downloadmodel.sh script fetches from this repository, resumes partial downloads, and points ./ds4flash.gguf at the selected variant. License MIT. The base model copyright is held by DeepSeek; the GGUFs are redistributed under the base model's release terms.

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerantirez
TypeLanguage models
Variants1
Runs withgguf
Based ondeepseek-ai/DeepSeek-V4-Flash
Released2026-04-26
Popularity2.1M downloads / month
Likes465
LicenceOpen weights

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
deepseek-v4-ggufGGUFWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys deepseek for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (deepseek below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Languages

en

Tags

gguf quantized deepseek deepseek-v4 deepseek-v4-flash moe mixture-of-experts 2-bit 4-bit iq2_xxs q2_k q4_k ds4 apple-silicon

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want deepseek on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More language models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms