Quantized GGUF models for GRMR-V3-G4B

This repository contains GGUF quantized versions of qingy2024/GRMR-V3-G4B.

IMPORTANT

If using llama.cpp, make sure to set the --jinja flag at the end of your llama-cli or llama-server command, otherwise it won't use the right chat template!

Available quantizations:

  • FP16 (full precision)
  • Q2_K
  • Q3_K_L
  • Q3_K_M
  • Q3_K_S
  • Q4_K_M
  • Q4_K_S
  • Q5_K_M
  • Q5_K_S
  • Q6_K
  • Q8_0

Original model

This is a quantized version of qingy2024/GRMR-V3-G4B.

Generated on

Fri Jun 6 05:40:02 UTC 2025

Downloads last month
377
GGUF
Model size
3.88B params
Architecture
gemma3
Hardware compatibility
Log In to view the estimation

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for qingy2024/GRMR-V3-G4B-GGUF

Quantized
(4)
this model

Collection including qingy2024/GRMR-V3-G4B-GGUF