| LLM Name | Seed OSS 36B Instruct AWQ |
| Repository ๐ค | https://huggingface.co/QuantTrio/Seed-OSS-36B-Instruct-AWQ |
| Base Model(s) | |
| Model Size | 36b |
| Required VRAM | 21.1 GB |
| Updated | 2025-09-27 |
| Maintainer | QuantTrio |
| Model Type | seed_oss |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | zh en |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| 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 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Seed OSS 36B Instruct 4bit | 512K / 20.2 GB | 617 | 2 |
| Seed Oss 36B Instruct Fp16 Mlx | 512K / 72.2 GB | 34 | 2 |
| Seed OSS 36B Instruct | 512K / 72.2 GB | 19192 | 419 |
| ...eed OSS 36B Instruct GPTQ Int4 | 512K / 21.1 GB | 604 | 4 |
| ...6B Base Instruct Karcher Merge | 512K / 72.1 GB | 18 | 3 |
| Seed OSS 36B Instruct | 512K / 72.2 GB | 19 | 2 |
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐