inkling

About

What inkling is

Read our How to Run Inkling Guide! Inkling 1. General Information Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages. The model is designed to be used by developers building AI-powered applications, including agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation systems, and is suitable for general-purpose conversational use, instruction-following, and other natural language and multimodal tasks. It is released with open weights to support research, fine-tuning and integration into third-party products by downstream developers. Languages: English, with general multilingual capabilities across other languages. 2. Getting Started For accessing Inkling via Tinker: You can get started by referring to the Tinker Cookbook here and associated documentation here. Inkling supports local deployment using the following open-source libraries: SGLang (docs, PR) vLLM (docs, PR) TokenSpeed (docs, PR) Unsloth (docs, PR) Huggingface (docs, PR) API access is also available through third party inference providers. 3. Model Properties Model type Multimodal autoregressive transformer Architecture type A 66-layer decoder-only transformer with a sparse Mixture-of-Experts (MoE) feed-forward backbone: each token is routed to 6 of 256 experts, plus 2 shared experts active on every token. Attention is a hybrid of local and global layers. The model is natively multimodal — images and video are encoded via a hierarchical patch encoder, and audio via discrete token encoding — with all modalities projected into a shared hidden space and processed jointly by the decoder. Parameters 975B total, 41B active Numerics support BF16 and NVFP4 Input modalities Inkling accepts text input in UTF-8 encoding, image input in any pixel-based format (with each dimension ideally between 40px and 4096px for optimal performance), and audio input in WAV format sampled at 16kHz (ideally under 20 minutes in length for optimal performance). Output modalities Inkling generates output as UTF-8 encoded text. 4. Training Trai

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys inkling for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (inkling below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"inkling","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More language models