Saiga Aya 23 35B Sft M1 D5 AWQ 4bit by IlyaGusev

 ยป  All LLMs  ยป  IlyaGusev  ยป  Saiga Aya 23 35B Sft M1 D5 AWQ 4bit   URL Share it on

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.

  4-bit   4bit   Awq   Cohere   Conversational   Endpoints compatible   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Saiga Aya 23 35b Sft M1 D5 AWQ 4bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Saiga Aya 23 35B Sft M1 D5 AWQ 4bit (IlyaGusev/saiga_aya_23_35b_sft_m1_d5_awq_4bit)
๐ŸŒŸ Advertise your project ๐Ÿš€

Saiga Aya 23 35B Sft M1 D5 AWQ 4bit Parameters and Internals

LLM NameSaiga Aya 23 35b Sft M1 D5 AWQ 4bit
Repository ๐Ÿค—https://huggingface.co/IlyaGusev/saiga_aya_23_35b_sft_m1_d5_awq_4bit 
Model Size35b
Required VRAM25.5 GB
Updated2025-12-03
MaintainerIlyaGusev
Model Typecohere
Model Files  9.2 GB: 1-of-5   4.9 GB: 2-of-5   5.0 GB: 3-of-5   4.9 GB: 4-of-5   1.5 GB: 5-of-5
AWQ QuantizationYes
Quantization Typeawq|4bit
Model ArchitectureCohereForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.1
Tokenizer ClassCohereTokenizer
Padding Token<PAD>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to Saiga Aya 23 35B Sft M1 D5 AWQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Aya 23 35B AWQ Ru V08K / 24 GB50
Aya 23 35B 8bit8K / 36.9 GB132
Aya 23 35B 4bit8K / 19.6 GB121
Aya 23 35B 5.0bpw H6 EXL28K / 27.8 GB71
Aya 23 35B 8.0bpw H8 EXL28K / 39.2 GB02
Aya 23 35B 4.0bpw H6 EXL28K / 23.4 GB31
...reForAI Aya 23 35B 5 0bpw EXL28K / 27.7 GB31
Aya 23 35B 3.0bpw H6 EXL28K / 19 GB50
Aya 23 35B 4.65bpw H6 EXL28K / 26.1 GB50
Aya 23 35B 6.0bpw H6 EXL28K / 32.1 GB50

Rank the Saiga Aya 23 35B Sft M1 D5 AWQ 4bit Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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  

What open-source LLMs or SLMs are you in search of? 51648 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260327b