Skip to content
Weights Not Walls
Menu

deepseek-ai

DeepSeek-V3-Base

Unreviewedfetched live from the Hub

Not reviewed: shown with only what the Hub data supports. Our rule was not met:

  • not in our snapshot: shown as the Hub lists it, without our checks

The reviewed rule

Size
684B parameterscounted from the safetensors header on the Hub
Licence
unknown, none given on the Hub
On the Hub since
25 Dec 2024the date the repo was created
Context length
Not known
Kind
Base model (no base model declared on the Hub)DeepseekV3ForCausalLM
On Hugging Face
deepseek-ai/DeepSeek-V3-Base39k downloads in the last 30 days, 1.7k likes

Scores

1 independent result on 1 eval set
PIQAReported

Epoch's name: DeepSeek-V3-Base. Best closed model on this set: gpt-4o-mini-2024-07-18, 88.7% (OpenAI). All 113 results

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.

Run it yourself

no conversions read for this model

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 4.0 GB, a rough allowance by model size, because we do not have this model's attention config. Choose a machine above to see a verdict for each format. Method

Estimated sizes no measured GGUF files for this model

From the parameter count and the bits per weight of each level (the median measured over the GGUF files in our snapshot, or the format's block size). Real files differ by a few per cent.

FormatSizeMemory neededRepo
Q4_K_M4.88 bits per weight, measured median388.8 GBestimated393.3 GB388.8 + 4.0 + 0.50
Q5_K_M5.71 bits per weight, measured median455.0 GBestimated459.5 GB455.0 + 4.0 + 0.50
Q6_K6.57 bits per weight, measured median523.5 GBestimated528.0 GB523.5 + 4.0 + 0.50
Q8_08.50 bits per weight, measured median677.6 GBestimated682.1 GB677.6 + 4.0 + 0.50

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
F8_E4M3original weights641.1 GBfile size645.6 GB641.1 + 4.0 + 0.50
hf download deepseek-ai/DeepSeek-V3-Base --local-dir DeepSeek-V3-Base

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub, fetched live 19 Nov 2026, 16:04 UTC. The repo. Found a mistake on this page? Tell us.