SE

Seed-Oss-36B-Instruct

SeedGGUF by unslothUpdated 2025-08-24
Download on Hugging Face
Parameters36.2B
Context512K
Layers64
Architectureseed_oss
Smallest quant8.5 GB
Quick answer

Seed-Oss-36B-Instruct 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 26 quants, from 8.5 GB (IQ1_S) to 72.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

36B parameter LLM with long‑context and reasoning focus

Seed‑OSS‑36B‑Instruct is a 36‑billion‑parameter causal language model. It is trained with up to 512K context tokens and optimized for reasoning, agentic tasks, and international use. The model is released under Apache‑2.0.

Good at

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

Limits

  • Large VRAM requirement for higher quants
  • No vision capability
  • Requires 8‑k context for memory estimates

Best for

  • Complex reasoning workflows
  • Agentic task automation
  • Multilingual content generation

Who it’s for. Developers and researchers needing a powerful, open‑source model for long‑context reasoning and agentic applications. The model is suitable for those who can allocate sufficient GPU memory and prefer an Apache‑2.0 licensed solution.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S8.5 GB 11.1 GB
Too big Get file →
IQ1_M9.1 GB 11.7 GB
Too big Get file →
IQ2_XXS10.2 GB 12.8 GB
Too big Get file →
IQ2_M12.7 GB 15.4 GB
Too big Get file →
Q2_K13.6 GB 16.3 GB
Too big Get file →
Q2_K_L13.8 GB 16.4 GB
Too big Get file →
Q2_K_XL14.0 GB 16.7 GB
Too big Get file →
IQ3_XXS14.3 GB 16.9 GB
Too big Get file →
Q3_K_S15.9 GB 18.5 GB
Too big Get file →
Q3_K_M17.6 GB 20.3 GB
Too big Get file →
Q3_K_XL18.0 GB 20.7 GB
Too big Get file →
IQ4_XS19.5 GB 22.2 GB
Too big Get file →
IQ4_NL20.6 GB 23.2 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_K_XL22.0 GB 24.7 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 →
Q5_K_XL25.6 GB 28.3 GB
Too big Get file →
Q6_K29.7 GB 32.3 GB
Too big Get file →
Q6_K_XL31.8 GB 34.5 GB
Too big Get file →
Q8_038.4 GB 41.1 GB
Too big Get file →
Q8_K_XL42.9 GB 45.6 GB
Too big Get file →
BF1672.3 GB (2 parts) 75.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (8.47 GB) or IQ1_M (9.08 GB). For 12 GB VRAM, IQ2_XXS (10.16 GB) or IQ2_M (12.73 GB) are suitable. Higher quants such as Q4_K_XL (22.03 GB) require 24–25 GB VRAM.

What GPU do you need for Seed-Oss-36B-Instruct?

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: the best quant that fits is IQ1_M (9.1 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_M (12.7 GB file, about 15.4 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_XL (25.6 GB file, about 28.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_K_XL (42.9 GB file, about 45.6 GB in use).

Which Seed-Oss-36B-Instruct quant should you choose?

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

The Q8_0 file is 38.4 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 8.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 byunsloth
FamilySeed
Licenseapache-2.0
Downloads (HF)7,596
Last updated2025-08-24

Frequently asked questions about Seed-Oss-36B-Instruct

How much VRAM does Seed-Oss-36B-Instruct 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-Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Seed-Oss-36B-Instruct GGUF?

It depends on the quant: IQ1_S is 8.5 GB, IQ1_M is 9.1 GB, IQ2_XXS is 10.2 GB, IQ2_M is 12.7 GB, Q2_K is 13.6 GB, Q2_K_L is 13.8 GB and 20 more.

What context length does Seed-Oss-36B-Instruct 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 GGUF?

The files are on Hugging Face in the unsloth/Seed-OSS-36B-Instruct-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 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‑Instruct on 8 GB VRAM?

Use the IQ1_S or IQ1_M quantized files; they fit within 8 GB VRAM with an estimated 11–12 GB memory usage at 8k context.

Does the model support image input?

No, Seed‑OSS‑36B‑Instruct does not have vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Seed-OSS-36B-Instruct

Similar models

Browse all →

More from unsloth

All by unsloth →

More Seed models

All Seed →

Other large models

All large models →