What GPU do I need to run thinkingmachines/Inkling?

952.4B parameters, published in BF16. View on Hugging Face

952.4B
Parameters
BF16
Native precision
InklingForConditionalGeneration
Architecture
image-text-to-text
Pipeline

Inkling is published by thinkingmachines on Hugging Face, with 197,452 downloads and 1,760 likes to date. It's a InklingForConditionalGeneration model built for image-text-to-text, published natively in BF16.

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
BF161773.9 GB2128.7 GBNo capable live offer found––
FP8 (quantized)887.0 GB1064.4 GBAMD MI300X6$15.77/hr
INT4 (quantized)443.5 GB532.2 GBAMD MI300X3$7.89/hr

A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.

INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.

Inkling: KV cache by context length

The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.

Grouped-query attention: every layer caches keys and values for a few shared KV heads. Cached per token: 270,336 bytes at 16-bit.

ContextKV cache, one sequence
4K1.0 GB
32K8.3 GB
128K33.0 GB
1M (model maximum)264.0 GB

Computed from the layer, head and window counts in the model's own configuration (thinkingmachines/Inkling), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.

Inkling: common questions

Can Inkling run on a single GPU?

Not on a desktop card. At BF16 it needs 2128.7 GB of VRAM, more than a single 32 GB desktop card holds. No card currently listed on the marketplace both supports BF16 and has enough VRAM for it, so how many it would take is not something this page can answer today.

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

More thinkingmachines models

All 2 thinkingmachines models: VRAM and GPU requirements

Alternatives at this size

Other models for image-text-to-text within about a third of Inkling's 952.4B parameters, from other model lines.

More on Inkling

Related reading: H100 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.

Your own GPU cloud accounts

One console for the GPU clouds you already rent from. Your keys stay on your machine.

$20 a month, flat

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.