Autotrain compatible Base model:dreadpoor/irix-12b-... Base model:merge:dreadpoor/iri... Base model:merge:yamatazen/blu... Base model:merge:yamatazen/eth... Base model:merge:yamatazen/lor... Base model:yamatazen/bluelight... Base model:yamatazen/ethereala... Base model:yamatazen/lorablate... Conversational Endpoints compatible Frankenmerge Merge Mergekit Mistral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Retreatcost/Ollpheist-12B
Ollpheist 12B 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)
Ollpheist 12B Parameters and Internals
| LLM Name | Ollpheist 12B |
| Repository 🤗 | https://huggingface.co/Retreatcost/Ollpheist-12B |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-09-21 |
| Maintainer | Retreatcost |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.53.2 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to Ollpheist 12B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 310835 | 132 |
| MN 12B Mag Mell R1 | 1000K / 24.5 GB | 64319 | 200 |
| Impish Nemo 12B | 1000K / 24.5 GB | 2076 | 43 |
| KansenSakura Radiance RP 12B | 1000K / 24.5 GB | 463 | 10 |
| Irix Mpf Stock | 1000K / 24.5 GB | 192 | 2 |
| SauerkrautLM Nemo 12B Instruct | 1000K / 24.5 GB | 47510 | 22 |
| Captain Eris Violet V0.420 12B | 1000K / 24.5 GB | 1997 | 54 |
| Captain Eris BMO Violent 12B | 1000K / 24.5 GB | 305 | 2 |
| Dans SakuraKaze V1.0.0 12B | 1000K / 24.5 GB | 63 | 19 |
| ...n Eris BMO Violent GRPO V0.420 | 1000K / 24.5 GB | 92 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Retreatcost/Ollpheist-12B .
Rank the Ollpheist 12B 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? 51507 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124