# Seed-OSS 36B Instruct: RAM and VRAM requirements

> Seed-OSS 36B Instruct is a 36B Seed-OSS model. At Q4_K_M it needs about **22.5 GB** to run and fits **12 of 40** tracked devices. Minimum to run: Nvidia GeForce RTX 4090 (24GB).

Last validated: 2026-08-03. Sources: Ollama, HuggingFace GGUF repos, vendor specs.

## Memory by quantization
| Quant | On disk | To run (4k context) |
| --- | --- | --- |
| Q4_K_M | 20.27 GB | ~22.5 GB |
| Q8_0 | 35.78 GB | ~38 GB |
| FP16 | 72.31 GB | ~74.5 GB |

Memory = weights + KV cache + ~0.8 GB runtime overhead, and varies ±15% with context length.

## Will it run on my device?
- **Apple M1 (8GB)** (8 GB): No, not enough memory
- **iPhone 17** (8 GB): No, not enough memory
- **iPhone 17 Pro** (12 GB): No, not enough memory
- **16GB RAM Laptop (CPU/iGPU only)** (16 GB): No, not enough memory
- **Google Pixel 10 Pro** (16 GB): No, not enough memory
- **Nvidia GeForce RTX 3090 (24GB)** (24 GB): Yes, but tight
- **Apple M4 Pro (48GB)** (48 GB): Yes, it runs
- **Apple M3 Ultra (256GB)** (256 GB): Yes, it runs (room for FP16)

Full table of all 40 devices: https://localmodel.run/model/seed-oss-36b

## How to run
Use LM Studio (Mac/Windows) or Ollama / vLLM (Linux).

## Details
- Parameters: 36B
- Default context: 512k tokens
- License: apache-2.0 (commercial use: yes)
- Released: 2025-08
- HuggingFace: 41,234 downloads/mo, 505 likes

## FAQ
### How much VRAM or RAM does Seed-OSS 36B Instruct need?
About 22.5 GB at Q4_K_M (weights 20.27 GB + KV cache + overhead) at a 4k context. Budget ~38 GB for Q8_0.
### Can Seed-OSS 36B Instruct run on a laptop?
Seed-OSS 36B Instruct is large; you need a high-memory Mac or a 24 GB+ GPU at Q4_K_M.
### Can I use Seed-OSS 36B Instruct commercially?
Yes, apache-2.0 permits commercial use.

Sources: https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct, https://huggingface.co/bartowski/ByteDance-Seed_Seed-OSS-36B-Instruct-GGUF
More: https://localmodel.run/model/seed-oss-36b