4-bit Autotrain compatible Base model:jondurbin/airoboros... Base model:quantized:jondurbin... Conversational Dataset:jondurbin/airoboros-3.... Gptq Llama Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Airoboros-c34B-3.1.2-GPTQ
Airoboros C34B 3.1.2 GPTQ Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Airoboros C34B 3.1.2 GPTQ Parameters and Internals
| LLM Name | Airoboros C34B 3.1.2 GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Airoboros-c34B-3.1.2-GPTQ |
| Model Name | Airoboros c34B 3.1.2 |
| Model Creator | Jon Durbin |
| Base Model(s) | |
| Model Size | 4.7b |
| Required VRAM | 17.7 GB |
| Updated | 2025-07-30 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.34.0 |
| Tokenizer Class | CodeLlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Airoboros C34B 3.1.2 GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Airoboros C34b 2.2.1 GPTQ | 16K / 17.7 GB | 5 | 2 |
| Airoboros C34B 2.2 GPTQ | 16K / 17.7 GB | 6 | 1 |
| Airoboros C34B 2.1 GPTQ | 16K / 17.7 GB | 8 | 12 |
| Llama3.1 Merged | 128K / 5.8 GB | 6 | 0 |
| EPFL TA Meister 4bit | 8K / 5.8 GB | 6 | 0 |
| Book 4bitV5 | 8K / 5.8 GB | 5 | 0 |
| Book 4bit | 8K / 5.8 GB | 6 | 0 |
| Llama3 Ko 4bit | 8K / 5.8 GB | 6 | 0 |
| Tenebra PreAlpha 128g 4BIT | 2K / 17.6 GB | 6 | 0 |
| ...loth Llama3.1 Instruct Bnb4bit | 128K / 5.8 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Airoboros-c34B-3.1.2-GPTQ .
Rank the Airoboros C34B 3.1.2 GPTQ Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 50262 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124