Downloads · 30 days
165
17% of all-time downloads
cyborgxx101/gemma4-vedic-opus-finetuned-v2-gguf
gemma4-vedic-opus-finetuned-v2-gguf is a text generation model from cyborgxx101. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
GGUF quantizations of the v2 scholarly Vedic fine-tune. See the MLX model repo for full details.
Downloads · 30 days
165
17% of all-time downloads
All-time downloads
961
Public
Repo size
43.9 GB
Likes
1
Public
Click a slice to open those files.
.gguf43.9 GB · 100%
From the Hugging Face model README
GGUF quantizations of the v2 scholarly Vedic fine-tune. See the MLX model repo for full details.
| File | Type | Size |
|---|---|---|
gemma-4-12b-vedic-v2-f16.gguf | F16 (float16) | 23.8 GB |
gemma-4-12b-vedic-v2-q8_0.gguf | Q8_0 (8-bit) | 12.7 GB |
gemma-4-12b-vedic-v2-q4_k_m.gguf | Q4_K_M (4-bit) | 7.0 GB |
./main -m gemma-4-12b-vedic-v2-q4_k_m.gguf \
--temp 0.2 \
--top-p 0.95 \
--repeat-penalty 1.15 \
-p "<|turn>user\nWhat is Ṛta in the Rig Veda?<turn|>\n<|turn>model\n"
Apache 2.0