deepseek-ai

DeepSeek-R1

Name: DeepSeek-R1
Author: deepseek-ai

← All models

684.5B parameters · mixture-of-experts · Reasoning · DeepSeek family

mit hash verified source matched revision pinned

Which version should I download?

Default pick: GGUF · UD-Q2_K_XL — Unsloth dynamic 2-bit (UD-Q2_K_XL) — accessible 671B (684.531B total, 256-expert MoE) giant lead (~211 GiB, 5 shards; preservation lane per DR-21). MIT.

Set your rig to confirm it fits and to see if a higher-quality quant runs fully on your hardware.

Set your rig

Quantizations

Why these quants? Which quant should I pick?

Format	Level	Size	Verdict	Est. speed	Quality note	Swarm	Download
GGUF	UD-Q2_K_XL	211.04 GB	Set your rig	—	Unsloth dynamic 2-bit (UD-Q2_K_XL) — accessible 671B (684.531B total, 256-expert MoE) giant lead (~211 GiB, 5 shards; preservation lane per DR-21). MIT.	2S / 0L webseed OK	Magnet .torrent

GGUF · UD-Q2_K_XL

211.04 GB

Set your rig

Est. speed: —
Swarm: 2S / 0L webseed OK

Unsloth dynamic 2-bit (UD-Q2_K_XL) — accessible 671B (684.531B total, 256-expert MoE) giant lead (~211 GiB, 5 shards; preservation lane per DR-21). MIT.

Magnet .torrent

Run it

Runtime completeness (UD-Q2_K_XL torrent): llama.cpp ✅ Ollama – vision sidecar –

– Ollama — runs the GGUF directly; no Modelfile bundled
– vision sidecar — not a vision model

Quant

Context / KV 8,192 tokens · FP16 set above the quant table

Generic commands (no rig set). GPU-offload values assume the model fits on your GPU — set your rig for values tuned to your hardware.

Start the server

llama-server -m DeepSeek-R1-UD-Q2_K_XL-00001-of-00005.gguf -c 8192 -ngl 999

Use llama-cli in place of llama-server for a one-shot prompt.

Save as Modelfile next to the GGUF (Modelfile)

FROM ./DeepSeek-R1-UD-Q2_K_XL-00001-of-00005.gguf
PARAMETER num_ctx 8192
PARAMETER num_gpu 999

Create

ollama create deepseek-ai-deepseek-r1 -f Modelfile

Run

ollama run deepseek-ai-deepseek-r1

GGUF is not a first-class vLLM format.

vLLM GGUF support is experimental and single-file only; prefer safetensors/GPTQ/AWQ for production. If you must, pass the .gguf path to `vllm serve` with --load-format gguf on a recent vLLM.

Load DeepSeek-R1-UD-Q2_K_XL-00001-of-00005.gguf, set the context length to 8192 tokens. Set GPU offload to Max (all layers).

Not an MLX-format quant.

MLX runs MLX-format weights only (Apple Silicon). This quant is not an MLX build.

Technical details

No template or sampling metadata recorded.

Evidence & provenance

Source

Provenance: https://huggingface.co/deepseek-ai/DeepSeek-R1
Revision pin: 56d4cbbb4d29f4355bab4b9a39ccb717a14ad5ad
Manifest: Present

License

Name: mit
Commercial use: yes
Access: Open

File hashes (SHA-256)

deepseek-r1-671b-ud-q2-k-xl/DeepSeek-R1-UD-Q2_K_XL-00001-of-00005.gguf 311b7e2b72da29daffbac5e5f5df9353b1b3be9879d22d1dc498ece99529cfe5
deepseek-r1-671b-ud-q2-k-xl/DeepSeek-R1-UD-Q2_K_XL-00002-of-00005.gguf 6b1b63ef53a397cb6ace27961165c1cfb82051b1ba42ade07405642ed096355d
deepseek-r1-671b-ud-q2-k-xl/DeepSeek-R1-UD-Q2_K_XL-00003-of-00005.gguf 26dc583b72212bd0c0c0a646e78bb0863abef173de26cef5d38c2b051e3aaec6
deepseek-r1-671b-ud-q2-k-xl/DeepSeek-R1-UD-Q2_K_XL-00004-of-00005.gguf 25427bd9a557f820cde553cfc5f6c911b6109322bd3dfa555ecbc0f0ad55c2f1
deepseek-r1-671b-ud-q2-k-xl/DeepSeek-R1-UD-Q2_K_XL-00005-of-00005.gguf 9983ab89fe131158b39704b61f07215ed7c9f847ae9e97225d6a9e74692f70d2
deepseek-r1-671b-ud-q2-k-xl/LICENSE 1c8f573e830ca9b3ebfeb7ace1823146e22b66f99ee223840e7637c9e745e1c7
deepseek-r1-671b-ud-q2-k-xl/README.md 753e8ae21b5d3a0a02676833848fba197e0e474acdaef30612db8d66f4c3582d

Performance reports

Real-world throughput reported by the community (and scraped sources).

View performance leaderboard

Reviews & presets

Reviews (0)

No reviews yet.

Sampler presets

No presets yet.

Community runtime reports

Unofficial, community-submitted "it loads for me" reports. These are not the official verified-working badge — an admin reviews reports before anything is marked officially verified.

No community reports yet.

Recommended download