DeepSeek-R1 (2025-01-20)
- Open weights
Prices
0 offerings · prices as listedNo priced offering is listed for this model yet.
Details
- Family
- deepseek-r
Run locally
Weights: deepseek-ai/DeepSeek-R1- Parameters 684.5B
- Active 51B (estimated) · 256 experts, 8 per token
- Native precision FP8
- Layers 61
- KV cache per token 69 KB
- Config positions 160K (config.json max_position_embeddings)
- Needs
- ≈ 356.1 GB (weights 338.7 + KV cache 0.5 + overhead 16.9)
- 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 | 641.3 GB | ≈ 673.9 | ✕Doesn’t fit | — |
| Q6_K | 523.5 GB | ≈ 550.2 | ✕Doesn’t fit | — |
| Q5_K_M | 453.4 GB | ≈ 476.6 | ✕Doesn’t fit | — |
| Q5_0 | 438.3 GB | ≈ 460.7 | ✕Doesn’t fit | — |
| Q4_K_M | 387.3 GB | ≈ 407.2 | ✕Doesn’t fit | — |
| Q4_0 | 358.6 GB | ≈ 377.0 | ✕Doesn’t fit | — |
| IQ4_XS | 338.7 GB | ≈ 356.1 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 311.6 GB | ≈ 327.7 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 243.8 GB | ≈ 256.6 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 239.1 GB | ≈ 251.5 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 164.2 GB | ≈ 172.9 | ✕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 6 × 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-R1 model card (opens in a new tab) huggingface.co · checked Nov 5, 2026
- DeepSeek | DeepSeek-R1 Release (opens in a new tab) deepseek.com · checked Oct 17, 2026
- deepseek-ai/DeepSeek-R1 config.json (opens in a new tab) huggingface.co · checked Nov 5, 2026
- deepseek-ai/DeepSeek-R1 files (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