LLM
Llama-3-2-3B-Instruct-Q2_K-2Bit
None|3000000000 parameters
Ultra-efficient 2-bit GGUF quantized Llama 3.2 3B Instruct model optimized for low-memory CPU inference with reduced storage footprint.
VARIANTS
0
formats available
SMALLEST
0 MB
best compressed
BEST ACCURACY
0%
top variant
DOWNLOADS
0
total
DOWNLOAD VARIANT
Llama-3-2-3B-Instruct-Q2_K-2Bit
SELECT FORMAT
BENCHMARKS
USAGE
HARDWARE GUIDE
MODEL CARD
VARIANT COMPARISON
Accuracy vs. Size Tradeoff
Every variant is benchmarked against the FP16 baseline. Choose the right balance of accuracy and footprint for your workflow.
Benchmarks are performed on representative hardware. Accuracy is relative to model FP16 baseline.
| VARIANT | FORMAT | SIZE | PERPLEXITY | ACCURACY | LATENCY | BEST FOR | DOWNLOAD |
|---|---|---|---|---|---|---|---|
| FP16 (baseline) | — | 1200.00 MB | -- | 100% | — | Reference only | — |
ACCURACY RETENTION BY VARIANT (%)
FILE SIZE BY VARIANT (MB)
FP16 base1200.00 MB