Inkling (BF16) — VRAM Requirements
Written by Jakub Rusinowski · Last updated July 16, 2026
How much GPU VRAM you need to run Inkling Inkling (BF16) by Thinking Machines locally, a 975B-parameter model. Figures are quantized weights + KV cache + framework overhead, computed from the model's parameter count and published architecture — not a throughput model. See /en/methodology.
Inkling (BF16) needs about 589 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 320.5 GB | 321.3 GB |
| Q3_K_M | 3.41 | 415.6 GB | 416.4 GB |
| Q4_K_M | 4.83 | 588.7 GB | 589.5 GB |
| Q5_K_M | 5.67 | 691.0 GB | 691.8 GB |
| Q6_K | 6.56 | 799.5 GB | 800.3 GB |
| Q8_0 | 8.50 | 1035.9 GB | 1036.7 GB |
| F16 | 16.00 | 1950.0 GB | 1950.8 GB |
Switch quantization in the interactive calculator, or see the full Inkling model page.
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.
Add this badge to your model card
Model creators: paste this into your Hugging Face model card README to link readers straight to this VRAM breakdown.
[](https://llmconfigurator.com/en/vram-calculator/inkling-bf16?utm_source=badge&utm_medium=referral&utm_campaign=readme_badge&utm_content=inkling-bf16)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.