Thinking Machines: Inkling Small.
Inkling-Small is an Apache 2.0 mixture-of-experts model, 276B total and 12B active, that takes text, images and short audio clips and returns text.
1× AMD MI300X · $0.50/hr.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
Variants in the Inkling family.
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
FP16
FP16 — half precision (default)
|
768 GB | $2.00/hr | — | Compare → | |
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
384 GB | $1.00/hr | — | Compare → | |
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
192 GB | $0.50/hr | 27.9 | Compare → |
What it costs per month across providers.
Estimate your monthly bill for Thinking Machines: Inkling Small across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Bill breakdown.
Rent the GPU instead of paying per token.
For an open-weights model like Thinking Machines: Inkling Small, you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month + your electricity rate × power draw.
Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.
About Thinking Machines: Inkling Small.
Inkling-Small is an Apache 2.0 open-weights model from Thinking Machines that takes text, images and audio and returns text. It has 276 billion parameters, 12 billion active, across 42 layers, routing each token to 6 of 256 experts plus 2 shared ones. Audio should be 16kHz WAV, ideally under 2 minutes. The maker aims it at developers building agents, coding assistants, chatbots and retrieval systems. It warns of hallucination, missed instructions and weaker results in long conversations, and advises human review for high-stakes use.