SE

Seed OSS 36B Instruct Unsloth

SeedGGUF by magiccodingmanUpdated 2025-12-03
Download on Hugging Face
Parameters36.2B
Context512K
Layers64
Architectureseed_oss
Smallest quant19.2 GB
Quick answer

Seed OSS 36B Instruct Unsloth needs about 21.9 GB of memory at MXFP4_MOE (a 19.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 19.2 GB (MXFP4_MOE) to 35.0 GB (MXFP4_MOE). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Seed OSS 36B Instruct Unsloth is a 36.2B-parameter Seed model in GGUF format, quantized by magiccodingman. Its trained context length is 512K tokens. The repository has 2 quant files, from 19.2 GB (MXFP4_MOE) to 35.0 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE19.2 GB 21.9 GB
Too big Get file →
MXFP4_MOE35.0 GB 37.7 GB
Too big Get file →

What GPU do you need for Seed OSS 36B Instruct Unsloth?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is MXFP4_MOE (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is MXFP4_MOE (19.2 GB file, about 21.9 GB in use).
  • 48 GB VRAM: the best quant that fits is MXFP4_MOE (35.0 GB file, about 37.7 GB in use).

Which Seed OSS 36B Instruct Unsloth quant should you choose?

MXFP4_MOE (19.2 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureseed_oss
Parameters36.2B
Layers64
Trained context524,288 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymagiccodingman
FamilySeed
Licenseapache-2.0
Downloads (HF)27
Last updated2025-12-03

Frequently asked questions about Seed OSS 36B Instruct Unsloth

How much VRAM does Seed OSS 36B Instruct Unsloth need?

About 21.9 GB at MXFP4_MOE with an 8K context window. That is the 19.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Seed OSS 36B Instruct Unsloth on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Seed OSS 36B Instruct Unsloth GGUF?

It depends on the quant: MXFP4_MOE is 19.2 GB, MXFP4_MOE is 35.0 GB.

What context length does Seed OSS 36B Instruct Unsloth support?

The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Seed OSS 36B Instruct Unsloth GGUF?

The files are on Hugging Face in the magiccodingman/Seed-OSS-36B-Instruct-Unsloth-MXFP4-Hybrid-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Seed OSS 36B Instruct Unsloth use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from magiccodingman

All by magiccodingman →

More Seed models

All Seed →

Other large models

All large models →