DeepSeek V3.2
8488°
Run this model
Offers / Ads
DeepSeek | 163,840 token context | $0.26/M input, $0.80/M output. DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and…DeepSeek | 163,840 token context | $0.26/M input, $0.80/M output. DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docsOpens in new tab
Guides for this model
Best local LLM by use case (October 2026): the right open model for every job
How much VRAM do I actually need for local AI?
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
DeepSeek V3.2 is a large open-weights model from DeepSeek built around three technical bets: a sparse attention mechanism that cuts compute costs on long contexts, a scaled reinforcement learning post-training framework, and an agentic task synthesis pipeline that wires reasoning into tool use. The maker reports performance in the GPT-5 class, with gold-medal results on the 2025 IMO and IOI. At under a dollar per million output tokens, it is a serious option if you need frontier-level reasoning without frontier-level bills.
Known for
- Gold-medal performance on 2025 IMO and IOI math and coding competitions.
- DeepSeek Sparse Attention reduces inference cost while holding long-context quality.
- Reasoning can be toggled on or off via a single boolean parameter.
- Agentic tool-use improved through large-scale synthetic training data.
- Open weights available on Hugging Face for self-hosted deployment.
Watch out for
- No Jinja chat template; you must use the maker's custom Python encoding scripts, which adds integration friction.
- Running a model of this scale locally demands serious hardware — check your VRAM before downloading.
- The high-compute variant DeepSeek-V3.2-Speciale is described separately; the standard V3.2 is the API-accessible version here.
Prompts to try
Hard competition math problem
A sequence is defined by a₁ = 1, a₂ = 1, and aₙ = aₙ₋₁ + aₙ₋₂ + n for n ≥ 3. Find a closed-form expression or recurrence for the general term, and prove your answer. Show every step of your reasoning.
Multi-step agentic plan
You have access to a web search tool, a Python interpreter, and a file-write tool. A user wants a weekly report on the top five open-source LLM releases, saved as a markdown file. Write the full tool-calling plan: which tools you call, in what order, with what inputs, and how you handle a failed search result.
Competitive programming task
Given an array of n integers, find the length of the longest subarray where the sum of elements is divisible by k. Write a solution in Python with O(n) time complexity, explain why it works, and include two test cases with expected outputs.
Compare with
- DeepSeek V4.1 FlashOpen-weights model1,048,576 token context · $0.04/M input, $0.68/M output
- DeepSeek V4 Flash 0731Open-weights model1,048,576 token context · $0.01/M input, $1.28/M output
- DeepSeek V4 Flash 0423Open-weights model1,048,576 token context · $0.09/M input, $0.18/M output
- DeepSeek V4 Pro 0813Open-weights model1,048,576 token context · $1.32/M input, $3.96/M output
More text models from deepseek
Questions people ask
- Are the weights open and can I run DeepSeek V3.2 locally?
- Yes, the weights are publicly available on Hugging Face under deepseek-ai/DeepSeek-V3.2. Be aware the model is very large, so local deployment requires substantial hardware.
- What does DeepSeek V3.2 cost and what is the context window?
- Via API it is priced at $0.26 per million input tokens and $0.80 per million output tokens, with a 163,840-token context window.
- How is V3.2 different from earlier DeepSeek V3 versions?
- V3.2 adds DeepSeek Sparse Attention for cheaper long-context inference, a scaled RL post-training framework, a new agentic task synthesis pipeline, and a revised chat template with a 'thinking with tools' capability not present in prior versions.
Captain's verdictA rare combination of open weights, sub-dollar output pricing, and genuine frontier-class reasoning — the integration overhead is real but worth it.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
Also ranked: #190 Hottest AI model · #56 Hottest Text / LLM model · #56 Hottest Text / LLM text model
Not this creator?
Get your own badge
DeepSeek V3.2 Popularity Trend
Heat score since 1 Dec 2025
Heat score
8,488°
This week
▲
1.6%
8,485° then, 8,488° now
This month
▲
7.4%
8,476° then, 8,488° now
Past year
n/a
Wasn't released/tracked
7,000°
Floor
The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.
+1,488°
OpenRouter tokens
914,260,079,186 tokens this model processed through OpenRouter in the last 30 days, prompts and answers together. Every 10,000,000 tokens count as one download in the download term, 91,426 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 8,488°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.
- 1Start at the floor.Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.7,000°running total
- 2Add the downloads.91,426 download-equivalents in all, from OpenRouter tokens. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.+1,488°8,488°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.8,488°
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.
DeepSeek V3.2 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153