%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Gryphe Pantheon Proto RP 1.8 30B A3B GGUF
This is a quantized version based on the Gryphe/Pantheon-Proto-RP-1.8-30B-A3B model, using llama.cpp for quantization, suitable for role-playing and text generation tasks.
Downloads 2,972
Release Time : 5/9/2025
Model Overview
This model is a quantized version of Pantheon-Proto-RP-1.8-30B-A3B, supporting ChatML format prompts, suitable for role-playing and dialogue generation tasks.
Model Features
Efficient Quantization
Uses llama.cpp for imatrix quantization, providing multiple quantization options to suit different hardware requirements.
Role-playing Optimization
The model is fine-tuned specifically for role-playing tasks, capable of generating high-quality dialogue content.
ChatML Support
Supports ChatML format prompts, making it easy to use in dialogue systems.
Model Capabilities
Text generation
Role-playing
Dialogue generation
Use Cases
Entertainment
Role-playing Games
Used to generate dialogue content in role-playing games, enhancing the gaming experience.
Generates natural and character-appropriate dialogue.
Dialogue Systems
Virtual Assistants
Used to build virtual assistants, generating natural and fluent dialogue responses.
Provides high-quality dialogue experiences.
🚀 Llamacpp imatrix Quantizations of Pantheon-Proto-RP-1.8-30B-A3B by Gryphe
This project offers quantized versions of the Pantheon-Proto-RP-1.8-30B-A3B model, enabling efficient deployment and inference with llama.cpp and related projects.
🚀 Quick Start
Running the Model
- Using LM Studio: You can run the quantized models in LM Studio.
- Using llama.cpp: Run the models directly with llama.cpp, or any other llama.cpp based project.
Prompt Format
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
✨ Features
- Quantization: Using llama.cpp release b5328 for quantization.
- Dataset: All quants are made using the imatrix option with a dataset from here.
📦 Installation
Download a File
You can download a specific file (not the whole branch) from the following table:
| Filename | Quant type | File Size | Split | Description |
|---|---|---|---|---|
| Pantheon-Proto-RP-1.8-30B-A3B-bf16.gguf | bf16 | 61.10GB | true | Full BF16 weights. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q8_0.gguf | Q8_0 | 32.48GB | false | Extremely high quality, generally unneeded but max available quant. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q6_K_L.gguf | Q6_K_L | 25.26GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q6_K.gguf | Q6_K | 25.10GB | false | Very high quality, near perfect, recommended. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q5_K_L.gguf | Q5_K_L | 21.94GB | false | Uses Q8_0 for embed and output weights. High quality, recommended. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q5_K_M.gguf | Q5_K_M | 21.74GB | false | High quality, recommended. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q5_K_S.gguf | Q5_K_S | 21.10GB | false | High quality, recommended. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q4_1.gguf | Q4_1 | 19.21GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q4_K_L.gguf | Q4_K_L | 18.86GB | false | Uses Q8_0 for embed and output weights. Good quality, recommended. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q4_K_M.gguf | Q4_K_M | 18.63GB | false | Good quality, default size for most use cases, recommended. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q4_K_S.gguf | Q4_K_S | 17.98GB | false | Slightly lower quality with more space savings, recommended. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q4_0.gguf | Q4_0 | 17.63GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| Pantheon-Proto-RP-1.8-30B-A3B-IQ4_NL.gguf | IQ4_NL | 17.39GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| Pantheon-Proto-RP-1.8-30B-A3B-IQ4_XS.gguf | IQ4_XS | 16.46GB | false | Decent quality, smaller than Q4_K_S with similar performance, recommended. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q3_K_XL.gguf | Q3_K_XL | 14.86GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q3_K_L.gguf | Q3_K_L | 14.58GB | false | Lower quality but usable, good for low RAM availability. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q3_K_M.gguf | Q3_K_M | 14.08GB | false | Low quality. |
| Pantheon-Proto-RP-1.8-30B-A3B-IQ3_M.gguf | IQ3_M | 14.08GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q3_K_S.gguf | Q3_K_S | 13.43GB | false | Low quality, not recommended. |
| Pantheon-Proto-RP-1.8-30B-A3B-IQ3_XS.gguf | IQ3_XS | 12.74GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| Pantheon-Proto-RP-1.8-30B-A3B-IQ3_XXS.gguf | IQ3_XXS | 12.22GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q2_K_L.gguf | Q2_K_L | 11.21GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| Pantheon-Proto-RP-1.8-30B-A3B-Q2_K.gguf | Q2_K | 10.91GB | false | Very low quality but surprisingly usable. |
| Pantheon-Proto-RP-1.8-30B-A3B-IQ2_M.gguf | IQ2_M | 10.43GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| Pantheon-Proto-RP-1.8-30B-A3B-IQ2_S.gguf | IQ2_S | 9.22GB | false | Low quality, uses SOTA techniques to be usable. |
| Pantheon-Proto-RP-1.8-30B-A3B-IQ2_XS.gguf | IQ2_XS | 9.14GB | false | Low quality, uses SOTA techniques to be usable. |
| Pantheon-Proto-RP-1.8-30B-A3B-IQ2_XXS.gguf | IQ2_XXS | 8.15GB | false | Very low quality, uses SOTA techniques to be usable. |
Downloading using huggingface-cli
Click to view download instructions
First, make sure you have hugginface-cli installed:
pip install -U "huggingface_hub[cli]"
Then, you can target the specific file you want:
huggingface-cli download bartowski/Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-GGUF --include "Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-Q4_K_M.gguf" --local-dir ./
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
huggingface-cli download bartowski/Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-GGUF --include "Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-Q8_0/*" --local-dir ./
You can either specify a new local-dir (Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-Q8_0) or download them all in place (./)
🔧 Technical Details
Embed/output weights
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
ARM/AVX information
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
Now, however, there is something called "online repacking" for weights. Details can be found in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
As of llama.cpp build b4282, you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
Additionally, if you want to get slightly better quality, you can use IQ4_NL thanks to this PR, which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed increase.
Click to view Q4_0_X_X information (deprecated)
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
Click to view benchmarks on an AVX2 system (EPYC7702)
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
|---|---|---|---|---|---|---|---|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 |
📄 License
This project is licensed under the apache-2.0 license.
Phi 2 GGUF
Other
Phi-2 is a small yet powerful language model developed by Microsoft, featuring 2.7 billion parameters, focusing on efficient inference and high-quality text generation.
Large Language Model Supports Multiple Languages
P
TheBloke
41.5M
205
Roberta Large
MIT
A large English language model pre-trained with masked language modeling objectives, using improved BERT training methods
Large Language Model English
R
FacebookAI
19.4M
212
Distilbert Base Uncased
Apache-2.0
DistilBERT is a distilled version of the BERT base model, maintaining similar performance while being more lightweight and efficient, suitable for natural language processing tasks such as sequence classification and token classification.
Large Language Model English
D
distilbert
11.1M
669
Llama 3.1 8B Instruct GGUF
Meta Llama 3.1 8B Instruct is a multilingual large language model optimized for multilingual dialogue use cases, excelling in common industry benchmarks.
Large Language Model English
L
modularai
9.7M
4
Xlm Roberta Base
MIT
XLM-RoBERTa is a multilingual model pretrained on 2.5TB of filtered CommonCrawl data across 100 languages, using masked language modeling as the training objective.
Large Language Model Supports Multiple Languages
X
FacebookAI
9.6M
664
Roberta Base
MIT
An English pre-trained model based on Transformer architecture, trained on massive text through masked language modeling objectives, supporting text feature extraction and downstream task fine-tuning
Large Language Model English
R
FacebookAI
9.3M
488
Opt 125m
Other
OPT is an open pre-trained Transformer language model suite released by Meta AI, with parameter sizes ranging from 125 million to 175 billion, designed to match the performance of the GPT-3 series while promoting open research in large-scale language models.
Large Language Model English
O
facebook
6.3M
198
1
A pretrained model based on the transformers library, suitable for various NLP tasks
Large Language Model
Transformers
Transformers1
unslothai
6.2M
1
Llama 3.1 8B Instruct
Llama 3.1 is Meta's multilingual large language model series, featuring 8B, 70B, and 405B parameter scales, supporting 8 languages and code generation, with optimized multilingual dialogue scenarios.
Large Language Model Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesL
meta-llama
5.7M
3,898
T5 Base
Apache-2.0
The T5 Base Version is a text-to-text Transformer model developed by Google with 220 million parameters, supporting multilingual NLP tasks.
Large Language Model Supports Multiple Languages
T
google-t5
5.4M
702
Featured Recommended AI Models