LLM EXPLORER 60,897 MODELS INDEXED

Seed OSS 36B Instruct 4bit by mlx-community

By mlx-community · 60 downloads
HF Repo ↗ Copy URL

Seed OSS 36B Instruct 4bit is an open-source language model by mlx-community. Features: 36b LLM, VRAM: 20.2GB, Context: 512K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.19.

  4-bit   4bit Base model:bytedance-seed/seed... Base model:quantized:bytedance...   Conversational   En   Instruct   Mlx   Quantized   Region:us   Safetensors   Seed oss   Sharded   Tensorflow   Vllm   Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/Seed-OSS-36B-Instruct-4bit 

Seed OSS 36B Instruct 4bit Parameters and Internals

LLM NameSeed OSS 36B Instruct 4bit
Repository 🤗https://huggingface.co/mlx-community/Seed-OSS-36B-Instruct-4bit 
Base Model(s)  Seed OSS 36B Instruct   ByteDance-Seed/Seed-OSS-36B-Instruct
Model Size36b
Required VRAM20.2 GB
Updated2026-07-26
Maintainermlx-community
Model Typeseed_oss
Instruction-BasedYes
Model Files  5.3 GB: 1-of-4   5.3 GB: 2-of-4   5.3 GB: 3-of-4   4.3 GB: 4-of-4
Supported Languagesen zh
Quantization Type4bit
Model ArchitectureSeedOssForCausalLM
Licenseapache-2.0
Context Length524288
Model Max Length524288
Transformers Version4.55.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<seed:pad>
Vocabulary Size155136
Torch Data Typebfloat16

Best Alternatives to Seed OSS 36B Instruct 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Seed Oss 36B Instruct Fp16 Mlx512K / 72.2 GB272
Seed OSS 36B Instruct512K / 72.2 GB45727505
Seed OSS 36B Instruct512K / 72.2 GB3823
Seed OSS 36B Instruct AWQ512K / 21.1 GB3208
...6B Base Instruct Karcher Merge512K / 72.1 GB382
...eed OSS 36B Instruct GPTQ Int4512K / 21.1 GB215
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Seed-OSS-36B-Instruct-4bit.