DeepSeek-V4-Pro (2026-04-24)
- Open weights
Prices
0 offerings · prices as listedNo priced offering is listed for this model yet.
Details
- Family
- deepseek-pro
Run locally
Weights: deepseek-ai/DeepSeek-V4-Pro- Parameters 1.6T
- Active 49B · 384 experts, 6 per token
- Native precision FP8
- Layers 61
- KV cache per token 122 KB
- Config positions 1024K (config.json max_position_embeddings)
- Needs
- ≈ 831.6 GB (weights 791.1 + KV cache 1.0 + overhead 39.6)
- Usable
- 21.6 GB (90% of its memory)
- Try
- it’s too large for this hardware; see the smallest that runs it below
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| FP8 (native)maker’s file | 805.3 GB | ≈ 846.6 | ✕Doesn’t fit | — |
| Q6_K | 1222.9 GB | ≈ 1285.0 | ✕Doesn’t fit | — |
| Q5_K_M | 1059.1 GB | ≈ 1113.0 | ✕Doesn’t fit | — |
| Q5_0 | 1023.7 GB | ≈ 1075.9 | ✕Doesn’t fit | — |
| Q4_K_M | 904.6 GB | ≈ 950.8 | ✕Doesn’t fit | — |
| Q4_0 | 837.6 GB | ≈ 880.4 | ✕Doesn’t fit | — |
| IQ4_XS | 791.1 GB | ≈ 831.6 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 727.8 GB | ≈ 765.1 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 569.6 GB | ≈ 599.0 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 558.4 GB | ≈ 587.3 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 383.4 GB | ≈ 403.6 | ✕Doesn’t fit | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): no single listed machine; about 14 × 80 GB GPUs.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by usThis model isn’t on any leaderboard we cite yet.
Changes
All changes →- New language model
Sources
- deepseek-ai/DeepSeek-V4-Pro model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- DeepSeek API change log (opens in a new tab) api-docs.deepseek.com · checked Nov 2, 2026
- deepseek-ai/DeepSeek-V4-Pro config.json (opens in a new tab) huggingface.co · checked Nov 2, 2026
- deepseek-ai/DeepSeek-V4-Pro files (opens in a new tab) huggingface.co · checked Nov 5, 2026
- deepseek-ai/DeepSeek-V4-Pro README.md (opens in a new tab) huggingface.co · checked Nov 5, 2026
DeepSeek’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
DeepSeek · China · deepseek.com
Related models
Snapshots, the same family and other models from this provider