Inkling
8348°
Run this model
Offers / Ads
Thinking Machines | 524,288 token context | $1.00/M input, $4.05/M output. Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.
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?
Open weights vs open source vs API-only: what you are actually allowed to do
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
Inkling is a 975B-parameter sparse mixture-of-experts model from Thinking Machines Lab, with 41B parameters active per token. Open weights, natively multimodal across text, image and audio, and built with a 524K-token context window, it targets developers building agentic pipelines, RAG systems and coding assistants. The MoE architecture keeps inference costs lower than the total parameter count suggests.
Known for
- Native text, image and audio understanding processed in a shared decoder
- 524,288-token context window — comfortably handles very long documents
- Sparse MoE routing: 41B active parameters from a 975B pool per token
- Open weights with recipes for SGLang, vLLM, Unsloth and Hugging Face
- Built explicitly for agentic and tool-use application development
Watch out for
- 975B total parameters means serious hardware requirements for local deployment — check your VRAM before downloading
- Audio input must be WAV at 16kHz; image dimensions should stay between 40px and 4096px for best results
- Weights are open but released under an Acceptable Use policy, not a fully permissive licence
Prompts to try
Agentic tool-use plan
You are building a research assistant that can search the web, read PDFs and send email summaries. Design the tool schema and agent loop in Python using function calling. Show the tool definitions, the main loop logic, and how you handle a tool returning an error mid-run.
Multimodal audio analysis
I'm attaching a short WAV recording of a customer support call. Transcribe it, identify the customer's main complaint, rate the agent's response quality on a scale of 1 to 5 with reasoning, and suggest one concrete improvement the agent could have made.
Long-document reasoning
Here is a 200-page technical specification document. Identify every place where a requirement contradicts another requirement, quote both passages, explain the conflict, and suggest which one should take precedence and why. Be exhaustive rather than selective.
Compare with
- Inkling SmallOpen-weights model524,288 token context · $0.45/M input, $1.20/M output
- GPT-6 LunaAPI-only model1,050,000 token context · $0.10/M input, $0.50/M output
- GPT-5.6 LunaAPI-only model1,050,000 token context · $0.20/M input, $1.20/M output
- Claude Opus 5.5API-only model1,000,000 token context · $4.00/M input, $20.00/M output
More text models from thinkingmachines
Questions people ask
- Can Inkling run locally?
- Yes — the weights are open and Thinking Machines publishes deployment recipes for SGLang, vLLM, Unsloth, TokenSpeed and Hugging Face. That said, the model has 975B total parameters, so you will need substantial hardware; check the VRAM guide before committing.
- What does Inkling cost via API?
- Thinking Machines prices it at $1.00 per million input tokens and $4.05 per million output tokens, with a 524,288-token context window. Third-party inference providers may price it differently.
- What makes Inkling different from a dense model of similar capability?
- Its sparse MoE architecture routes each token through only 41B of the 975B total parameters, which reduces the compute cost per token compared to a dense model of equivalent total size — though the full weight footprint still applies at load time.
Captain's verdictA serious open-weights frontier model for developers who need multimodal, long-context and agentic capability and are willing to provision the hardware for 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: #62 Hottest Text / LLM model · #62 Hottest Text / LLM text model
Not this creator?
Get your own badge
Inkling Popularity Trend
Heat score since 17 Jul 2026
Heat score
8,348°
This week
▲
7.2%
8,338° then, 8,348° now
This month
▲
41.5%
8,299° then, 8,348° 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.
+1,348°
OpenRouter tokens
311,584,593,096 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, 31,158 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 8,348°, 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.31,158 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.+1,348°8,348°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.8,348°
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.
Inkling 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