Skip to content
Local AI Wizard
Your machine
Theme

DeepSeek V4 Pro · 0813

DeepSeek · deepseek-ai/DeepSeek-V4-Pro-0813

Q4 file 849.7 GB (UD-Q4_K_XL) · Weights license: MIT

LiveBench · overall77.4 / 100#5 of 22 open models · 2026-06-25
Memory needed~1,200 GBQ4 weights + working room, before the machine's reserve
Parameters1,600 Bmanufacturer specification · 49B active
Context1,048,576 tokensPublished for this model

Quality

Quality · Overall

LiveBench 2026-06-25 · 0–100 · higher is better · this model outlined, #5 of 22

  • Color = publisher
  • Memory under review

Source: LiveBench 2026-06-25 · collected 2026-09-26 · open models without a score are not drawn (no score ≠ 0)

No result in LMArena 2026-10-22 Not in LMArena 2026-10-22

LiveBench categories

This model's mean per category · 0–100

85.8ReasoningReasoning77.2CodingCoding54.9Agentic CodingAgentic Coding95.1MathematicsMathematics79.2Data AnalysisData Analysis82.1LanguageLanguage67.7IFIF

Source: LiveBench 2026-06-25 · collected 2026-09-26 · open models without a score are not drawn (no score ≠ 0)

Reported by the publisher

9 results · DeepSeek's model card · read 2026-10-25
Terminal Bench 2.1
87.9
NL2Repo
61.5
Cybergym
83.3
DeepSWE
62.7
Toolathlon-Verified
74.1
Agents' Last Exam
25.7
AutomationBench (Public)
31.8
DSBench-FullStack †
71.1
Every reported result9
DSBench-Hard †
67.2

Values as printed on the card, with the publisher's own settings (card section: Introduction); column “DeepSeek-V4-Pro-0813”. Not comparable across publishers and not used in any ranking. Model card

Run it

Run it

File UD-Q4_K_XL · 849.7 GB · 20 parts · unsloth/DeepSeek-V4-Pro-0813-GGUF · What is Q4?

llama-server -hf unsloth/DeepSeek-V4-Pro-0813-GGUF:UD-Q4_K_XL
  1. Install llama.cpp
  2. Run the command above
  3. Ask at localhost:8080: Explain what a context window is, in two sentences.

Quality × memory

Quality × memory

LiveBench 2026-06-25 overall vs. Q4 planning memory (log scale) · 18 open models

  • This model
  • Color = publisher
60708081632641282565121,0242,0484,096Memory needed · Q4 · model only (GB, log)LiveBenchSmaug AgenticQwen3.8 MaxSmaug MiniDeepSeek V4 Pro · 0813

Memory = the model's own figure: parameters × 0.625 bytes + 20% working room, before any machine's reserve; with a chosen machine, the total there with its reserve (25% of memory, 2 to 8 GB; 2 GB per graphics card). An estimate, not measured VRAM. LiveBench 2026-06-25

Runs on

More memory than any profile in the catalog

Even the largest profile (8 × 80 GB, aggregated) is below this planning estimate. Multi-node setups are outside this catalog.

DeepSeek V4 Pro · 0813 is a text model from DeepSeek with 1,600B parameters, 49B of them active per token (mixture of experts). It was released on August 13, 2026 and reads up to 1,048,576 tokens of context. Its Q4 weights plus working room come to about 1,200 GB, more than the fast memory of every reference machine. We collected 2 downloadable GGUF files from one publisher; the most downloaded GGUF source is unsloth's. It scores 77.4 overall in LiveBench 2026-06-25.

On the reference machines

DeepSeek V4 Pro · 0813 on the reference machines
Where Q4 sits
Mac mini M2 · 8 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,202 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 16 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,204 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 24 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,206 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 32 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,208 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M5 Pro · 64 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,208 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac Studio M5 Max · 128 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,208 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,208 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 4060 · 8 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,202 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 3060 · 12 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,202 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 5080 · 16 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,202 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 4090 · 24 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,202 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 5090 · 32 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,202 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
DGX H100 · 8 × 80 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~1,216 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column

The file column uses the site's quant ladder (Q8_0 to Q3_K_M, MLX 8 to 4-bit on a Mac): the largest collected file whose size × 1.2 plus the context cache and the machine's reserve fits the fast memory. Planning estimates, not measured runs.

Plan another quantization or context

Consider it for

Compare DeepSeek V4 Pro · 0813 using its publisher card and the LiveBench 2026-06-25 snapshot. This is quality evidence, not local speed.

Check first

The Q4 weights plus working room come to about 1200 GB from 1,600B stated parameters, before the machine's reserve (Runs on adds it per machine). It is not a measured minimum; context, batch size, runtime and quantization change actual memory use.

Versions to download

Files you can download for this checkpoint. The section opens on the most downloaded collected GGUF source, unsloth, at UD-Q4_K_XL. Sizes are the Hub's published bytes. What is Q4?

GGUF · the only format collected

unsloth

unsloth/DeepSeek-V4-Pro-0813-GGUF · UD-Q4_K_XL/DeepSeek-V4-Pro-0813-UD-Q4_K_XL-00001-of-00020.gguf · 849.7 GB

Run this file

llama-server -hf unsloth/DeepSeek-V4-Pro-0813-GGUF:UD-Q4_K_XL
lms get https://huggingface.co/unsloth/DeepSeek-V4-Pro-0813-GGUF
  • Ollama: Ollama's documented hf.co form covers single-file GGUFs; this file has 20 parts
  • mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac

Quality scores on this page belong to the original checkpoint; these files are not scored or ranked. File sizes read 2026-10-23 · download counts read 2026-10-17 · commands: Hugging Face Hub docs: Use Ollama with any GGUF model · llama.cpp server README (-hf <user>/<model>[:quant]) · LM Studio docs: lms get with a Hugging Face URL · mlx-lm README (mlx_lm.generate --model)

Fine-tunes, adapters and other versions1 fine-tunes
Quantized versions
12
Fine-tunes
1
Adapters · merges
0 · 0

Browse them on the Hugging Face model tree · read 2026-10-23

Uncensored and abliterated versions0

Some community uploads remove the model's safety refusals. Quality may drop, the original publisher does not support them, claims about them are the uploader's, and the original license still applies. This site never recommends or ranks them.

0 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

The memory needed above is the Q4 load before a machine's reserve. Formula: parameters × 0.625 bytes, plus 20% working allowance; each machine then adds its system reserve: 25% of unified or system memory, 2 to 8 GB, or 2 GB per GPU on dedicated cards. This is neither measured VRAM nor checkpoint download size.

Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

vLLM · model card · How to Run with vLLM
vllm serve deepseek-ai/DeepSeek-V4-Pro-0813 \
  --trust-remote-code --kv-cache-dtype fp8 --block-size 256 \
  --data-parallel-size 4 --enable-expert-parallel \
  --moe-backend deep_gemm_mega_moe \
  --attention-config '{"use_fp4_indexer_cache": true}' \
  --speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'
SGLang · model card · How to Run with SGLang
sglang serve \
  --trust-remote-code \
  --model-path deepseek-ai/DeepSeek-V4-Pro-0813 \
  --tp 4 \
  --moe-runner-backend flashinfer_mxfp4 \
  --speculative-algorithm DSPARK \
  --mem-fraction-static 0.90 \
  --chunked-prefill-size 4096 \
  --swa-full-tokens-ratio 0.1 \

Evidence level: Generic estimate only; no execution reproduced by this site.

Publisher sampling defaults
temperature 1 · top_p 1generation_config.json · read 2026-10-23source
Chat template markers
— Chat template not read for this checkpoint
Before downloading
  1. Check the exact checkpoint and license linked here.
  2. Confirm a compatible runtime and precision or quantization for your platform.
  3. Allow for context, batch size and any extra media components beyond the weights.

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task and modality
language and reasoning · text
Count and basis
1,600B · manufacturer specification · 49B active
Context
1,048,576 tokens published for this model
Architecture
MoE
Released
Change Log | DeepSeek API Docs · read 2026-10-09source
Runtime and precision
No local execution verified.
Commercial use
Allowed MIT license text (SPDX) · read 2026-10-18license text
Every stored field11 fields
Revision checked
72e1d3230f6c080a530b0a1d46f8eb4602340597
Architecture
DeepseekV4ForCausalLM
Library
transformers
Hub task tag
text-generation
Formats
safetensors
Access
Open download
Publisher kind
Official
Repository created
2026-08-13creation is not the model's release
Repository updated
2026-08-13a commit is not a release date
Hub downloads (30 days) · likes
150,272 · 899this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Catalog reviewed: 2026-09-30. Benchmark release: 2026-06-25; snapshot collected: 2026-09-26.