SE

Seed OSS 36B Base

SeedGGUF by mradermacherUpdated 2025-12-16
Download on Hugging Face
Parameters36.2B
Context512K
Layers64
Architectureseed_oss
Smallest quant0.0 GB
Quick answer

Seed OSS 36B Base needs about 24.4 GB of memory at Q4_K_M (a 21.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.0 GB to 29.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Seed OSS 36B Base – 36.2B parameter LLM with 512K native context

Seed OSS 36B Base is a 36.2B parameter causal language model from ByteDance’s Seed Team. It supports up to 512K context tokens and is released under Apache‑2.0. The model is optimized for reasoning, agentic tasks and international use.

Good at

  • Long‑context reasoning
  • Agentic tool‑using
  • International language support

Limits

  • Requires large VRAM for full precision
  • No vision capabilities
  • License is Apache‑2.0

Best for

  • Research on long‑context LLMs
  • Developing agentic applications
  • Benchmarking reasoning tasks

Who it’s for. Researchers and developers needing a large, open‑source model with extensive context. The model is suitable for academic projects and production systems that can accommodate its memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S8.1 GB 10.7 GB
Too big Get file →
IQ1_M8.7 GB 11.4 GB
Too big Get file →
IQ2_XXS9.9 GB 12.6 GB
Too big Get file →
IQ2_XS10.9 GB 13.6 GB
Too big Get file →
IQ2_S11.6 GB 14.3 GB
Too big Get file →
IQ2_M12.5 GB 15.2 GB
Too big Get file →
Q2_K_S12.6 GB 15.3 GB
Too big Get file →
Q2_K13.6 GB 16.3 GB
Too big Get file →
IQ3_XXS14.1 GB 16.8 GB
Too big Get file →
IQ3_XS15.1 GB 17.7 GB
Too big Get file →
Q3_K_S15.9 GB 18.5 GB
Too big Get file →
IQ3_S15.9 GB 18.5 GB
Too big Get file →
IQ3_M16.5 GB 19.1 GB
Too big Get file →
Q3_K_M17.6 GB 20.3 GB
Too big Get file →
Q3_K_L19.1 GB 21.8 GB
Too big Get file →
IQ4_XS19.5 GB 22.1 GB
Too big Get file →
Q4_020.6 GB 23.3 GB
Too big Get file →
Q4_K_S20.7 GB 23.3 GB
Too big Get file →
Q4_K_M21.8 GB 24.4 GB
Too big Get file →
Q4_122.8 GB 25.4 GB
Too big Get file →
Q5_K_S25.0 GB 27.6 GB
Too big Get file →
Q5_K_M25.6 GB 28.2 GB
Too big Get file →
Q6_K29.7 GB 32.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 20.62 GB, estimated 23.3 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (21.76 GB, 24.4 GB memory) is a good balance. If you have 16 GB VRAM, Q5_K_S (24.97 GB, 27.6 GB memory) offers higher quality while staying within budget.

What GPU do you need for Seed OSS 36B Base?

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: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ1_M (8.7 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K_S (12.6 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_S (20.7 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (25.6 GB file, about 28.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (29.7 GB file, about 32.3 GB in use).

Which Seed OSS 36B Base quant should you choose?

Q4_K_M is the usual starting point for Seed OSS 36B Base: it balances file size and quality well. Here it is a 21.8 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

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 bymradermacher
FamilySeed
Licenseapache-2.0
Downloads (HF)1,815
Last updated2025-12-16

Frequently asked questions about Seed OSS 36B Base

How much VRAM does Seed OSS 36B Base need?

About 24.4 GB at Q4_K_M with an 8K context window. That is the 21.8 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 Base on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: file is 0.0 GB, IQ1_S is 8.1 GB, IQ1_M is 8.7 GB, IQ2_XXS is 9.9 GB, IQ2_XS is 10.9 GB, IQ2_S is 11.6 GB and 18 more.

What context length does Seed OSS 36B Base 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 Base GGUF?

The files are on Hugging Face in the mradermacher/Seed-OSS-36B-Base-i1-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 Base 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.

Can I run Seed OSS 36B Base on 8 GB VRAM?

Use the Q4_0 quant; it requires about 23.3 GB memory at 8 k context, which is beyond 8 GB VRAM, so it is not feasible without further quantization.

Does this model support vision tasks?

No, Seed OSS 36B Base is a text‑only causal language model.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Seed-OSS-36B-Base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Seed models

All Seed →

Other large models

All large models →