What are the hardware requirements for Seed Oss 36B Base Gptq?

Seed Oss 36B Base Gptq requires approximately 21 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 Base Gptq and how large is it?

Seed Oss 36B Base Gptq is developed by ronantakizawa, 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 Base Gptq?

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

Seed Oss 36B Base Gptq by ronantakizawa — VRAM 21GB, 512K context

Name: Seed Oss 36B Base Gptq
Author: ronantakizawa

Seed Oss 36B Base Gptq is an open-source language model by ronantakizawa. Features: 36b LLM, VRAM: 21GB, Context: 512K, License: apache-2.0, Quantized, LLM Explorer Score: 0.29.

4-bit Base model:bytedance-seed/seed... Base model:quantized:bytedance... Compressed-tensors Conversational En Endpoints compatible Gptq Llm-compressor Quantized Region:us Safetensors Seed-oss Seed oss Sharded Tensorflow Vllm W4a16

Model Card on HF 🤗: https://huggingface.co/ronantakizawa/seed-oss-36b-base-gptq

Seed Oss 36B Base Gptq Parameters and Internals

LLM Name	Seed Oss 36B Base Gptq
Repository 🤗	https://huggingface.co/ronantakizawa/seed-oss-36b-base-gptq
Base Model(s)	Seed OSS 36B Base ByteDance-Seed/Seed-OSS-36B-Base
Model Size	36b
Required VRAM	21 GB
Updated	2026-10-07
Maintainer	ronantakizawa
Model Type	seed_oss
Model Files	19.4 GB: 1-of-2 1.6 GB: 2-of-2
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	SeedOssForCausalLM
License	apache-2.0
Context Length	524288
Model Max Length	524288
Transformers Version	4.55.0
Tokenizer Class	TokenizersBackend
Padding Token	<seed:pad>
Vocabulary Size	155136
Torch Data Type	bfloat16

Rank the Seed Oss 36B Base Gptq 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

Best Alternatives to Seed Oss 36B Base Gptq

Best Alternatives	Context / RAM	Downloads	Likes
...eed OSS 36B Instruct GPTQ Int4	512K / 21.1 GB	21	5
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	512K / 72.2 GB	49981	505
Spoomplesmaxx Mockingbird 36B	512K / 72.2 GB	770	0
Hermes 4.3 36B	512K / 72.2 GB	15957	277
Seed OSS 36B Base	512K / 72.2 GB	31034	69
Seed OSS 36B Base WoSyn	512K / 72.2 GB	657	54
Seed OSS 36B Instruct	512K / 72.2 GB	382	3
Seed OSS 36B Instruct AWQ	512K / 21.1 GB	320	8