πŸ“‹ Model Description


base_model:
  • Steelskull/L3.3-Electra-R1-70b
pipeline_tag: text-generation library_name: transformers quantized_by: ddh0

Steelskull/L3.3-Electra-R1-70b-GGUF

This repo provides several GGUF imatrix quantizations of Steelskull/L3.3-Electra-R1-70b.

#### Quantizations (worst to best)

  • IQ2M
  • IQ3XS
  • IQ3M
  • Q4KS
  • IQ4XS
  • Q4KM
  • Q5KS
  • Q5KM
  • Q6K
  • Q80

The imatrix was generated using the same calibration data as Bartowski, and both the calibration data as well as the imatrix itself are provided here.

πŸ“‚ GGUF File List

πŸ“ Filename πŸ“¦ Size ⚑ Download
L3.3-Electra-R1-70b-IQ2_M.gguf
LFS Q2
22.46 GB Download
L3.3-Electra-R1-70b-IQ3_M.gguf
LFS Q3
29.74 GB Download
L3.3-Electra-R1-70b-IQ3_XS.gguf
LFS Q3
27.29 GB Download
L3.3-Electra-R1-70b-IQ4_XS.gguf
LFS Q4
35.3 GB Download
L3.3-Electra-R1-70b-Q4_K_M.gguf
Recommended LFS Q4
39.6 GB Download
L3.3-Electra-R1-70b-Q4_K_S.gguf
LFS Q4
37.58 GB Download
L3.3-Electra-R1-70b-Q5_K_M.gguf
LFS Q5
46.52 GB Download
L3.3-Electra-R1-70b-Q5_K_S.gguf
LFS Q5
45.32 GB Download
L3.3-Electra-R1-70b-Q6_K-split-00001-of-00002.gguf
LFS Q6
27.58 GB Download
L3.3-Electra-R1-70b-Q6_K-split-00002-of-00002.gguf
LFS Q6
26.33 GB Download
L3.3-Electra-R1-70b-Q8_0-split-00001-of-00002.gguf
LFS Q8
35.72 GB Download
L3.3-Electra-R1-70b-Q8_0-split-00002-of-00002.gguf
LFS Q8
34.1 GB Download