DeepSeek V4 Pro 0813
deepseek-aimittext

DeepSeek V4 Pro 0813

Updated Nov 21, 2026
Parameters
1.7T
Context
1,048,576
License
mit
Q4 GGUF
849.68 GB
Updated
Nov 21, 2026

Q4 GGUF download: unsloth/DeepSeek-V4-Pro-0813-GGUF - 849.68 GB on disk, read 2026-10-31. VRAM figures above are estimates; this is the actual file size.

Intelligence benchmarks

Artificial Analysis indexes - compared with the best open and proprietary models

Intelligence

23.1

AA Index

Coding

15.9

AA Index

Agentic

34.1

AA Index

Intelligence Index - DeepSeek V4 Pro 0813 vs. the field

Best open-weight models (you can run locally) and leading proprietary models for context.

Claude Fable 5.2
64.6
closed
GPT-6.2 Astra
62.1
closed
Gemini 4 Neon
61.4
closed
Gemini 4 Carbon
60
closed
Claude Opus 5.5
59.1
closed
Kimi K3.1 Pro
46.5
open
DeepSeek V4.1 Flash 1017
32.6
open
DeepSeek V4 Pro 0813
23.1
open

Coding Index comparison

GPT-6.2 Astra
55
closed
Claude Fable 5.2
53.3
closed
Gemini 4 Neon
52.1
closed
Claude Opus 5.5
51.7
closed
GPT-6.2 Sol
50.7
closed
Kimi K3.1 Pro
42.1
open
DeepSeek V4.1 Flash 1017
30.6
open
DeepSeek V4 Pro 0813
15.9
open

Agentic Index comparison

Gemini 4 Neon
56.3
closed
Gemini 4 Carbon
53.6
closed
GPT-6.2 Astra
53.5
closed
Kimi K3.1 Pro
52.3
open
Gemini 4 Hydrogen
52.2
closed
Muse Wonder Full
52
closed
MiniMax-M3.1-Flash
46.7
open
DeepSeek V4 Pro 0813
34.1
open

Benchmark data from Artificial Analysis · updated 2026-11-21.

Hosted API cost & speed

What it costs to rent this model instead of running it locally

MetricValue
Input (per 1M tokens)$1.32
Output (per 1M tokens)$3.96
Median speed (hosted API)72 tok/s

Median across hosted providers, measured by Artificial Analysis - updated 2026-11-21. Local llama.cpp speed depends on your hardware — see the hardware pages for estimates.

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
GPQA Diamond92.8
HLE41
SciCode51

Source: Artificial Analysis component evals - updated 2026-11-21.

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Too big for 24 GB at any quant
0 of 4 quantizations fit DeepSeek V4 Pro 0813 with real runtime overhead.
Q4_K_M
957 GB
Q5_K_M
1172 GB
Q8_0
1766 GB
FP16
3301 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve deepseek-ai/DeepSeek-V4-Pro-0813

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

DeepSeek V4 Pro 0813 is a 1650.5B-parameter mit model from DeepSeek. It scores 23.1 on the Artificial Analysis Intelligence Index (coding 15.9). At Q4_K_M it needs roughly 957 GB of VRAM, placing it in the 48 GB+ / multi-GPU hardware tier.

BenchmarksLink to this section

Artificial Analysis Intelligence Index - DeepSeek V4 Pro 0813 vs. leading closed models:

ModelIntelligenceCodingGPQA
DeepSeek V4 Pro 081323.115.992.8
Claude Fable 5.264.653.1-
GPT-6.2 Astra62.152.9-
Gemini 4 Neon61.452.1-
Gemini 4 Carbon6050.4-
Claude Opus 5.559.151.7-

Source: Artificial Analysis (2026-11-21).

PopularityLink to this section

DeepSeek V4 Pro 0813 has 245 downloads in the last month on HuggingFace and 433 likes.

From the community

What users are saying

“I haven't tried DeepSeek V4 Pro 0813 yet. Recent experience tells me that larger models are worth it in non-obvious ways. MiMo-V2.5-Pro solved problems that DeepSeek V4 Flash 0731 couldn't solve for me: for example, adding a live counter for elided reasoning lines to a terminal-based coding harness.”

“Exactly! I am not opposed to cloud-based models, but I do only stick to open-weight models because I know I can move my whole stack to local (given enough hardware) and continue development without any of the LLM interaction contracts being broken.”

“Before DeepSeek-V4-Pro-0813's price goes up, I expect a surge of frantic traffic — hope the servers can hold up.”

Frequently asked

Quick answers to common questions

How much VRAM does DeepSeek V4 Pro 0813 need?

DeepSeek V4 Pro 0813 with 1.7T parameters needs approximately 957 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is DeepSeek V4 Pro 0813 better than other deepseek-ai models?

DeepSeek V4 Pro 0813 has 1.7T parameters with 1,048,576 context - a strong choice for long-context, general-chat.

What license is DeepSeek V4 Pro 0813 under?

DeepSeek V4 Pro 0813 is released under the mit license, making it suitable for most commercial and personal projects.

What hardware runs DeepSeek V4 Pro 0813 well?

With 1.7T parameters, DeepSeek V4 Pro 0813 requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for DeepSeek V4 Pro 0813?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1172 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can DeepSeek V4 Pro 0813's context window handle?

DeepSeek V4 Pro 0813 supports a 1,048,576-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.

What models compete with DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 competes with other 825B–2476B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec