Downloads · 30 days
37
14% of all-time downloads
angaadi-base-v5-gguf
bosmet/angaadi-base-v5-gguf
angaadi-base-v5-gguf is a machine learning model from bosmet. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
GGUF quants of bosmet/angaadi-base-v5 for local llama.cpp / Ollama deployment.
All-time downloads
259
Public
Repo size
7.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf7.6 GB · 100%
At a glance
- Access
- Public
- Created
- Apr 29, 2026
- Updated
- Apr 29, 2026
- SHA
- de364fe6
Model card
From the Hugging Face model README
bosmet/angaadi-base-v5-gguf
GGUF quants of bosmet/angaadi-base-v5 for local llama.cpp / Ollama deployment.
Quants in this repo
| Quant | Size | Notes |
|---|---|---|
f16 | 3.45 GB | Full precision (no quality loss). Use as the gold reference. |
q8_0 | 1.83 GB | 8-bit, <1% quality loss. Best when VRAM allows. |
q5_k_m | 1.26 GB | 5-bit balanced. ~1-2% quality loss; a good default. |
q4_k_m | 1.11 GB | 4-bit production default. ~3-5% loss; runs anywhere. |
Use with Ollama
ollama pull hf.co/bosmet/angaadi-base-v5-gguf:f16
# Optional: bake in the Angaadi system prompt + temp 0
cat > Modelfile <<EOF
FROM hf.co/bosmet/angaadi-base-v5-gguf:f16
SYSTEM "You are Angaadi's customer assistant. Answer concisely using the facts available."
PARAMETER temperature 0
PARAMETER num_ctx 1024
EOF
ollama create angaadi-qa -f Modelfile
ollama run angaadi-qa "tea"
Use with llama.cpp directly
llama-server -m model.f16.gguf -c 1024 --port 8080
License & private repo
Inherits from base — same private/internal use.
- Created
- Apr 29, 2026
- Updated
- Apr 29, 2026