Edit model card

rishiraj/smol-3b-GGUF

Quantized GGUF model files for smol-3b from rishiraj

Name Quant method Size
smol-3b.fp16.gguf fp16 6.04 GB
smol-3b.q2_k.gguf q2_k 1.30 GB
smol-3b.q3_k_m.gguf q3_k_m 1.51 GB
smol-3b.q4_k_m.gguf q4_k_m 1.85 GB
smol-3b.q5_k_m.gguf q5_k_m 2.15 GB
smol-3b.q6_k.gguf q6_k 2.48 GB
smol-3b.q8_0.gguf q8_0 3.21 GB

Original Model Card:

smol-3b

See how open weights instead of open source feel like!

Downloads last month
49
GGUF
Model size
3.02B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for afrideva/smol-3b-GGUF

Adapter
(1)
this model