30B Epsilon AWQ is an open-source language model by TheBloke. Features: 30b LLM, VRAM: 17.6GB, Context: 2K, License: other, Quantized, LLM Explorer Score: 0.09.
4-bit Adventure Alpaca Awq Base model:calderaai/30b-epsil... Base model:quantized:calderaai... Cot Hippogriff Instruct Llama Manticore Merge Mix Quantized Region:us Roleplay Rp Safetensors Sharded Story Supercot Superhot Tensorflow Uncensored Vicuna Wizardlm
Model Card on HF 🤗: https://huggingface.co/TheBloke/30B-Epsilon-AWQ
30B Epsilon AWQ 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)
30B Epsilon AWQ Parameters and Internals
| Model Type |
| |||
| Input Output |
|
| LLM Name | 30B Epsilon AWQ |
| Repository 🤗 | https://huggingface.co/TheBloke/30B-Epsilon-AWQ |
| Model Name | 30B Epsilon |
| Model Creator | Caldera AI |
| Base Model(s) | |
| Model Size | 30b |
| Required VRAM | 17.6 GB |
| Updated | 2026-04-09 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.28.1 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to 30B Epsilon AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| 30B Lazarus AWQ | 2K / 17.6 GB | 16 | 4 |
| Hippogriff 30B Chat AWQ | 2K / 17.6 GB | 15 | 1 |
| ...ge Llama 30B Instruct 2048 AWQ | 2K / 17.6 GB | 11 | 2 |
| GPlatty 30B AWQ | 2K / 17.6 GB | 6 | 2 |
| Platypus 30B AWQ | 2K / 17.6 GB | 6 | 2 |
| VicUnlocked 30B LoRA AWQ | 2K / 17.6 GB | 5 | 2 |
| SuperPlatty 30B AWQ | 2K / 17.6 GB | 6 | 0 |
| LLaMA 30B AWQ | 0K / 17.6 GB | 29 | 3 |
| Tenebra 30B Alpha01 FP16 | 16K / 65 GB | 1833 | 9 |
| Tenebra 30B Alpha01 4BIT | 16K / 19.4 GB | 65 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/30B-Epsilon-AWQ .
Rank the 30B Epsilon AWQ 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? 52758 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a