Run Inkling locally
Inkling is 975B parameters (41B active per token — a mixture-of-experts, so it still needs room for all 975B in memory). Here's the VRAM it needs at each quantization, the smallest GPU that fits, and how a self-hosted box compares with the cheapest verified API.
VRAM by quantization
| Quantization | VRAM needed | Fits on | Notes |
|---|---|---|---|
| int4 (Q4) | 585 GB | 8× H100 (640 GB) ($13.84/hr) | smallest footprint, minor quality loss |
| int8 (Q8) | 1170 GB | multi-node (>640 GB) | near-lossless |
| fp16 (full) | 2340 GB | multi-node (>640 GB) | reference quality |
VRAM ≈ params × bytes/param × 1.2 (overhead). See the fullmethod and break-even calculator.
Self-host vs API
Cheapest API for Inkling is $5.05 / 1M tokens(blended) via BaseTen. Running it yourself in int4 fits a8× H100 (640 GB) at $13.84/hr — about $10,103.2/month at 24/7. Those two lines cross at roughly 2.0B tokens/month: below that the API wins on cost, above it the dedicated GPU does (assuming you keep it busy). Tune your own volume in the break-even calculator.
Run it at home
In int4, Inkling needs 585 GB — more than any consumer desktop or Apple machine we track holds, so at home it means a multi-GPU server. Renting cloud GPUs by the hour, or the API, is the practical route. See the machines table for the ceiling.
Get the weights
Quantized builds on the model hubs — links search live, so they track new builds as they appear:
- GGUF builds llama.cpp · Ollama · LM Studio
- AWQ builds GPU serving (vLLM)
- GPTQ builds GPU serving
- MLX builds Apple silicon
- Ollama library one-command local run