What are the hardware requirements for Seed OSS 36B Instruct?

Seed OSS 36B Instruct requires approximately 72.2 GB of VRAM and supports a context window of 512K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Seed OSS 36B Instruct and how large is it?

Seed OSS 36B Instruct is developed by ByteDance-Seed, a model with 36b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Seed OSS 36B Instruct?

Seed OSS 36B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Seed OSS 36B Instruct by ByteDance-Seed — VRAM 72.2GB, 512K context

Name: Seed OSS 36B Instruct
Author: ByteDance-Seed

Seed OSS 36B Instruct is an open-source language model by ByteDance-Seed. Features: 36b LLM, VRAM: 72.2GB, Context: 512K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.3.

Conversational Deploy:azure Endpoints compatible Eval-results Instruct Region:us Safetensors Seed oss Sharded Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct

Seed OSS 36B Instruct Parameters and Internals

LLM Name	Seed OSS 36B Instruct
Repository 🤗	https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct
Base Model(s)	Seed OSS 36B Base ByteDance-Seed/Seed-OSS-36B-Base
Model Size	36b
Required VRAM	72.2 GB
Updated	2026-09-10
Maintainer	ByteDance-Seed
Model Type	seed_oss
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-15 5.0 GB: 2-of-15 4.8 GB: 3-of-15 4.9 GB: 4-of-15 4.8 GB: 5-of-15 4.9 GB: 6-of-15 4.8 GB: 7-of-15 4.9 GB: 8-of-15 4.8 GB: 9-of-15 4.9 GB: 10-of-15 4.8 GB: 11-of-15 4.9 GB: 12-of-15 4.8 GB: 13-of-15 4.9 GB: 14-of-15 4.0 GB: 15-of-15
Supported Languages	en zh
Model Architecture	SeedOssForCausalLM
License	apache-2.0
Context Length	524288
Model Max Length	524288
Transformers Version	4.55.0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<seed:pad>
Vocabulary Size	155136
Torch Data Type	bfloat16

Rank the Seed OSS 36B Instruct capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the Seed OSS 36B Instruct

Model	Likes	Downloads	VRAM
Seed OSS 36B Instruct AWQ	8	320	21 GB
Seed OSS 36B Instruct 4bit	3	60	20 GB
...eed OSS 36B Instruct GPTQ Int4	5	21	21 GB
Seed Oss 36B Instruct Fp16 Mlx	2	27	72 GB

Best Alternatives to Seed OSS 36B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Seed OSS 36B Instruct	512K / 72.2 GB	382	3
...6B Base Instruct Karcher Merge	512K / 72.1 GB	38	2
Seed OSS 36B Instruct 4bit	512K / 20.2 GB	60	3
Seed Oss 36B Instruct Fp16 Mlx	512K / 72.2 GB	27	2
Seed OSS 36B Instruct AWQ	512K / 21.1 GB	320	8
...eed OSS 36B Instruct GPTQ Int4	512K / 21.1 GB	21	5