Downloads · 30 days
50
12% of all-time downloads
sieve-llama-3.2-1b-GGUF
azatvaliev/sieve-llama-3.2-1b-GGUF
sieve-llama-3.2-1b-GGUF is a text generation model from azatvaliev. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as llama3.2.
GGUF quantizations of azatvaliev/sieve-llama-3.2-1b, a fine-tune of meta-llama/Llama-3.2-1B for SQL WHERE clause generation.
All-time downloads
432
Public
Repo size
5.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf5.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- llama3.2
- Access
- Public
- Created
- Mar 1, 2026
- Updated
- Mar 1, 2026
- SHA
- 981d48a1
Try a prompt
Base models
Model card
From the Hugging Face model README
sieve-llama-3.2-1b-GGUF
GGUF quantizations of azatvaliev/sieve-llama-3.2-1b, a fine-tune of meta-llama/Llama-3.2-1B for SQL WHERE clause generation.
See the model card for usage details and input/output format.
Quantizations
| File | Quant | Size | Recommendation |
|---|---|---|---|
| model-q4_k_m.gguf | Q4_K_M | 0.8 GB | Best speed, still retains high quality |
| model-q6_k.gguf | Q6_K | 1.0 GB | Balanced, but not recommended |
| model-q8_0.gguf | Q8_0 | 1.2 GB | Best quality, no perceptible loss from F16 |
Usage
# Download
huggingface-cli download azatvaliev/sieve-llama-3.2-1b-GGUF model-q4_k_m.gguf
# Run
llama-server --model model-q4_k_m.gguf -c 4096 -ngl 99 --port 8080
- Task
- Text Generation
- Library
- gguf
- License
- llama3.2
- Languages
- en
- Created
- Mar 1, 2026
- Updated
- Mar 1, 2026