Inkling Small — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
Thinking Machines' smaller open model: a mixture-of-experts with 276B parameters (266B in the published files) and 12B active per token. It takes text, images and audio, writes text, and has a 1M-token context. Apache-2.0; vLLM, SGLang and TokenSpeed recipes on the card.
Inkling Small needs about 161 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 88.6 GB | — | Too big | |
| Q3_K_M 3.41 bpw | 114.5 GB | — | Too big | |
| Q4_K_M 4.83 bpw | 161.8 GB | — | Too big | |
| Q5_K_M 5.67 bpw | 189.7 GB | — | Too big | |
| Q6_K 6.56 bpw | 219.3 GB | — | Too big | |
| Q8_0 8.50 bpw | 283.8 GB | — | Too big | |
| F16 16.00 bpw | 533.1 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Inkling Small VRAM calculator →
Get Inkling Small running
The cheapest catalogued GPU that runs Inkling Small is the Apple M3 Ultra (512 GB).
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run Inkling Small
Install Ollama, then run:
ollama run inklingSpecifications
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parameters
- 276 Billion (12B active)
- Context window
- 1,048,576
- Architecture
- Mixture-of-Experts (256 experts, 6 active), 7 global + 35 sliding-window (512) layers, image and audio encoders
- Provider
- Thinking Machines
- Licence
- Apache-2.0
- Availability
- Weights downloadable
- Practical deployment
- Workstation (large unified memory or pro GPU)
- Specified at
- Q4_K_M
- System RAM
- 256 GB
- Record updated
- 2026-11-11
Commercial use permitted. No usage restrictions beyond attribution.
Limits and caveats
- The card gives 276B parameters; the published safetensors hold 266.0B, and memory here is sized from the files.
See also Inkling (NVFP4)
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Can I run Inkling Small on my GPU?
Other Inkling sizes
Inkling Small — frequently asked questions
How much VRAM does Inkling Small need?
About 161 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Inkling Small run on an RTX 4090 (24 GB)?
No. Inkling Small needs about 161 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run Inkling Small locally?
Install Ollama and run `ollama run inkling`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Inkling come in?
Inkling (NVFP4) (589 GB), Inkling (BF16) (589 GB), Inkling Small (161 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.