DeepSeek V3.2 671B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
671B MoE with 37B active parameters. Improved over V3 with better tool-use, function-calling, and long-context handling. MIT licensed. DEPRECATED: superseded by DeepSeek V4 (1M context, MIT) — reported retiring 2026-07-24.
DeepSeek V3.2 671B needs about 414 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 | 226.6 GB | — | Too big | |
| Q3_K_M 3.41 bpw | 293.4 GB | — | Too big | |
| Q4_K_M 4.83 bpw | 414.9 GB | — | Too big | |
| Q5_K_M 5.67 bpw | 486.9 GB | — | Too big | |
| Q6_K 6.56 bpw | 563.1 GB | — | Too big | |
| Q8_0 8.50 bpw | 729.2 GB | — | Too big | |
| F16 16.00 bpw | 1371.4 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. DeepSeek V3.2 671B VRAM calculator →
Get DeepSeek V3.2 671B running
DeepSeek V3.2 671B is not practical on a single consumer GPU: it needs about 414.4 GB at Q4_K_M, more than any single device in our catalogue holds with headroom. How multi-GPU inference works, or rent a multi-GPU server by the hour:
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 DeepSeek V3.2 671B
Install Ollama, then run:
ollama run deepseek-v3.2:671b-q4Specifications
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
- Parameters
- 671 Billion (37B active)
- Context window
- 128,000
- Architecture
- MoE
- Provider
- DeepSeek
- Licence
- MIT
- Practical deployment
- Multi-GPU server
- Specified at
- Q4_K_M
- System RAM
- 256 GB
- Record updated
- 2026-02-28
Commercial use permitted. No usage restrictions beyond attribution.
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 DeepSeek V3.2 671B on my GPU?
DeepSeek V3.2 671B — frequently asked questions
How much VRAM does DeepSeek V3.2 671B need?
About 414 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 DeepSeek V3.2 671B run on an RTX 4090 (24 GB)?
No. DeepSeek V3.2 671B needs about 414 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 DeepSeek V3.2 671B locally?
Install Ollama and run `ollama run deepseek-v3.2:671b-q4`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does DeepSeek V3.2 come in?
DeepSeek V3.2 671B (414 GB), DeepSeek V3.2 685B (414 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.