LLM
Phi-3-mini-4k-instruct-4Bit
None|3800000000 parameters
4-bit GGUF quantized version of Microsoft's Phi-3 Mini 4K Instruct model optimized for efficient local inference with low memory usage and strong reasoning capabilities.
VARIANTS
0
formats available
SMALLEST
0 MB
best compressed
BEST ACCURACY
0%
top variant
DOWNLOADS
0
total
DOWNLOAD VARIANT
Phi-3-mini-4k-instruct-4Bit
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) | — | 2283.00 MB | -- | 100% | — | Reference only | — |
ACCURACY RETENTION BY VARIANT (%)
FILE SIZE BY VARIANT (MB)
FP16 base2283.00 MB