deepseek-ai

DeepSeek-R1-0528

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

Mixture-of-experts — what it means for memory & speed → Long context — how it uses memory →
mit hash verified source matched revision pinned

Which version should I download?

Default pick: GGUF · UD-Q2_K_XL — Unsloth UD-Q2_K_XL dynamic 2-bit quant of DeepSeek-R1-0528 (684.531B total, 256-expert MoE) — recommended balanced pick. 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? What do these mean?

GGUF · UD-Q2_K_XL

233.86 GB

Set your rig
Est. speed
—
Swarm
1S / 0L webseed OK

Unsloth UD-Q2_K_XL dynamic 2-bit quant of DeepSeek-R1-0528 (684.531B total, 256-expert MoE) — recommended balanced pick. MIT.

Magnet .torrent

Want a different quant? Request it on the board →

Runs fully on

Apple M3 Ultra (512 GB) · UD-Q2_K_XL

Green = the model's best quant fits fully in GPU/unified memory at 8K context. Tap a card for its full "what runs on it" page.

Context

Advertised 160k · usable ≈ 64–128k (measured — LongBench v2)

How we know

Evidence grade: measured — a published evaluation we can cite, with task and length stated.

LongBench v2 leaderboard: 56.7 overall w/ CoT; long bucket 51.4 — lower than original R1 (59.3). Release note publishes no context statements.

Reviewed on Jul 18, 2026.

Capabilities (as declared by the maintainer): reasoning tool calling

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

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-R1-0528-UD-Q2_K_XL-00001-of-00006.gguf -c 8192 -ngl 999

Use llama-cli in place of llama-server for a one-shot prompt. This model compresses its KV cache, but only on llama.cpp b5137 (April 2025) or newer AND a GGUF converted after that date. Older files -- including some still-popular DeepSeek-R1 and V3-0324 quants -- fall back to the uncompressed layout and use about 5 MB per token instead of 70 KB. Check the quant repo date if long context is the point.

Save as Modelfile next to the GGUF (Modelfile) 
FROM ./DeepSeek-R1-0528-UD-Q2_K_XL-00001-of-00006.gguf
PARAMETER num_ctx 8192
PARAMETER num_gpu 999
PARAMETER stop "<｜end▁of▁sentence｜>"
PARAMETER temperature 0.6
PARAMETER top_p 0.95
# Chat template: Ollama uses the template embedded in the GGUF (no TEMPLATE directive needed).
Create 
ollama create deepseek-ai-deepseek-r1-0528 -f Modelfile
Run 
ollama run deepseek-ai-deepseek-r1-0528

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.

transformers does not load GGUF weights.

GGUF weights run under llama.cpp, Ollama or LM Studio.

Load DeepSeek-R1-0528-UD-Q2_K_XL-00001-of-00006.gguf, set the context length to 8192 tokens. Set GPU offload to Max (all layers).

MLX runs MLX-format weights only (Apple Silicon). This quant is a GGUF build.

GGUF weights run under llama.cpp, Ollama or LM Studio.

Technical details

Chat template

{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '

' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + content + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
' + '```json' + '
' + tool['function']['arguments'] + '
' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
' + '```json' + '
' + tool['function']['arguments'] + '
' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'
' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
' + '```json' + '
' + tool['function']['arguments'] + '
' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'
<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}

Sampling defaults

top_p
0.95
temperature
0.6

Stop strings

<｜end▁of▁sentence｜>

Evidence & provenance

Source

Provenance
https://huggingface.co/deepseek-ai/DeepSeek-R1-0528
Revision pin
4236a6af538feda4548eca9ab308586007567f52
Manifest
Present

License

Name
mit
Commercial use
yes
Access
Open

How verification works →

File hashes (SHA-256)

  • deepseek-r1-0528-ud-q2-k-xl/DeepSeek-R1-0528-UD-Q2_K_XL-00001-of-00006.gguf 89f68bb6419306d71d6673868c86166161e4789426641a8059de2a7591c377d8
  • deepseek-r1-0528-ud-q2-k-xl/DeepSeek-R1-0528-UD-Q2_K_XL-00002-of-00006.gguf 2233f06c0d12548b5c23a06c6602645b19707f7c780a7eaa29667847e7f2cca9
  • deepseek-r1-0528-ud-q2-k-xl/DeepSeek-R1-0528-UD-Q2_K_XL-00003-of-00006.gguf 1346d009eed02e1c94f2446e805cb2e96528c66fefd63d1176c50a1ea3b06db7
  • deepseek-r1-0528-ud-q2-k-xl/DeepSeek-R1-0528-UD-Q2_K_XL-00004-of-00006.gguf 4fc7fbc476358469c4c0932d28af6e5867ec33cf803cbc9d1d56c47b20e45686
  • deepseek-r1-0528-ud-q2-k-xl/DeepSeek-R1-0528-UD-Q2_K_XL-00005-of-00006.gguf 1443d966973cc0d63e262edcb94dfde9c8be2951043588a023e02ebf6c07c3a4
  • deepseek-r1-0528-ud-q2-k-xl/DeepSeek-R1-0528-UD-Q2_K_XL-00006-of-00006.gguf 43b00c3a057a438e215f9fdca19787fb4e18701cdf7bc054585cb6014d168f96
  • deepseek-r1-0528-ud-q2-k-xl/LICENSE f2c6c602815669d292889e5be8c802f2ed950653b77999b1584e8e6aed25d040
  • deepseek-r1-0528-ud-q2-k-xl/README.md aac62a327dcc249441b491b49855a9c69c5122b1b69a34de69983155da318e84

Explore further

Also consider

Get an email when a better quant fits your rig.

Set your rig once; we'll alert you when a new or better-fitting build lands.

Set your rig

Performance reports

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

View performance leaderboard
Community

Reviews, sampler presets and community runtime reports. Be the first to contribute.

Reviews (0)

Log in to write a structured review of this model.

No reviews yet.

Sampler presets

Log in to share a sampler preset or vote on 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.

Log in to report whether a quant loads in your runtime.

No community reports yet.

selected to compare · pick at least 2

Compare ()