Run DeepSeek V3.1 Terminus locally
DeepSeek V3.1 Terminus is 671B parameters (37B active per token — a mixture-of-experts, so it still needs room for all 671B 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) | 402.6 GB | 8× H100 (640 GB) ($15.92/hr) | smallest footprint, minor quality loss |
| int8 (Q8) | 805.2 GB | multi-node (>640 GB) | near-lossless |
| fp16 (full) | 1610.4 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 DeepSeek V3.1 Terminus is $1.25 / 1M tokens(blended) via AtlasCloud. Running it yourself in int4 fits a8× H100 (640 GB) at $15.92/hr — about $11,621.6/month at 24/7. Those two lines cross at roughly 9.3B 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, DeepSeek V3.1 Terminus needs 402.6 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
License: open weights under MIT · terms. Compare all providers on the deepseek-v3.1-terminus API page.