Saiga Aya 23 35B Sft M1 D5 AWQ 4bit is an open-source language model by IlyaGusev. Features: 35b LLM, VRAM: 25.5GB, Context: 8K, Quantized, LLM Explorer Score: 0.15.
| LLM Name | Saiga Aya 23 35b Sft M1 D5 AWQ 4bit |
| Repository ๐ค | https://huggingface.co/IlyaGusev/saiga_aya_23_35b_sft_m1_d5_awq_4bit |
| Model Size | 35b |
| Required VRAM | 25.5 GB |
| Updated | 2025-12-03 |
| Maintainer | IlyaGusev |
| Model Type | cohere |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq|4bit |
| Model Architecture | CohereForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.1 |
| Tokenizer Class | CohereTokenizer |
| Padding Token | <PAD> |
| Vocabulary Size | 256000 |
| Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Aya 23 35B AWQ Ru V0 | 8K / 24 GB | 5 | 0 |
| Aya 23 35B 8bit | 8K / 36.9 GB | 13 | 2 |
| Aya 23 35B 4bit | 8K / 19.6 GB | 12 | 1 |
| Aya 23 35B 5.0bpw H6 EXL2 | 8K / 27.8 GB | 7 | 1 |
| Aya 23 35B 8.0bpw H8 EXL2 | 8K / 39.2 GB | 0 | 2 |
| Aya 23 35B 4.0bpw H6 EXL2 | 8K / 23.4 GB | 3 | 1 |
| ...reForAI Aya 23 35B 5 0bpw EXL2 | 8K / 27.7 GB | 3 | 1 |
| Aya 23 35B 3.0bpw H6 EXL2 | 8K / 19 GB | 5 | 0 |
| Aya 23 35B 4.65bpw H6 EXL2 | 8K / 26.1 GB | 5 | 0 |
| Aya 23 35B 6.0bpw H6 EXL2 | 8K / 32.1 GB | 5 | 0 |
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