Downloads · 30 days
23
17% of all-time downloads
libraos/Cydonia-24B-v4.3-AWQ
Cydonia-24B-v4.3-AWQ is a text generation model from libraos. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Mirror These weights are byte-identical to tacodevs/Cydonia-24B-v4.3-AWQ, re-hosted here for use on Meganova infrastructure. The AWQ 4-bit quantization is the work of tacodevs (formerly Irvollo), not ours — we have no…
Downloads · 30 days
23
17% of all-time downloads
All-time downloads
134
Public
Parameters
23.6B
14.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors14.2 GB · 100%
How the weights are stored.
I3222.2B · 94%
From the Hugging Face model README
Mirror
These weights are byte-identical to
tacodevs/Cydonia-24B-v4.3-AWQ, re-hosted here for use on Meganova infrastructure. The AWQ 4-bit quantization is the work of tacodevs (formerlyIrvollo), not ours — we have not modified the weights. Byte-identity was verified against the upstream shard sizes.If you have no specific reason to pull from this repo, use
tacodevs/Cydonia-24B-v4.3-AWQinstead.
AWQ 4-bit quantization of TheDrummer/Cydonia-24B-v4.3.
Works with vLLM, Transformers, and other AWQ-compatible inference engines.
# vLLM
vllm serve meganovaai/Cydonia-24B-v4.3-AWQ --quantization awq_marlin --dtype float16
# Transformers
from awq import AutoAWQForCausalLM
model = AutoAWQForCausalLM.from_quantized("meganovaai/Cydonia-24B-v4.3-AWQ")
Cydonia v4.3 by TheDrummer — a Mistral Small 3.1 24B fine-tune optimized for roleplay and creative writing.