metadata
base_model: google/gemma-3-1b-it
inference: false
library_name: transformers
license: gemma
model_creator: Google
model_name: gemma-3-1b-it
quantized_by: Second State Inc.
pipeline_tag: text-generation
gemma-3-1b-it-GGUF
Original Model
Run with LlamaEdge
- LlamaEdge version: coming soon
- Context size:
128000
Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| gemma-3-1b-it-Q2_K.gguf | Q2_K | 2 | 690 MB | smallest, significant quality loss - not recommended for most purposes |
| gemma-3-1b-it-Q3_K_L.gguf | Q3_K_L | 3 | 752 MB | small, substantial quality loss |
| gemma-3-1b-it-Q3_K_M.gguf | Q3_K_M | 3 | 722 MB | very small, high quality loss |
| gemma-3-1b-it-Q3_K_S.gguf | Q3_K_S | 3 | 689 MB | very small, high quality loss |
| gemma-3-1b-it-Q4_0.gguf | Q4_0 | 4 | 720 MB | legacy; small, very high quality loss - prefer using Q3_K_M |
| gemma-3-1b-it-Q4_K_M.gguf | Q4_K_M | 4 | 806 MB | medium, balanced quality - recommended |
| gemma-3-1b-it-Q4_K_S.gguf | Q4_K_S | 4 | 781 MB | small, greater quality loss |
| gemma-3-1b-it-Q5_0.gguf | Q5_0 | 5 | 808 MB | legacy; medium, balanced quality - prefer using Q4_K_M |
| gemma-3-1b-it-Q5_K_M.gguf | Q5_K_M | 5 | 851 MB | large, very low quality loss - recommended |
| gemma-3-1b-it-Q5_K_S.gguf | Q5_K_S | 5 | 836 MB | large, low quality loss - recommended |
| gemma-3-1b-it-Q6_K.gguf | Q6_K | 6 | 1.01 GB | very large, extremely low quality loss |
| gemma-3-1b-it-Q8_0.gguf | Q8_0 | 8 | 1.07 GB | very large, extremely low quality loss - not recommended |
| gemma-3-1b-it-f16.gguf | f16 | 16 | 2.01 GB |
Quantized with llama.cpp b4875