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)

IQ2_M
IQ3_XS
IQ3_M
Q4_K_S
IQ4_XS
Q4_K_M
Q5_K_S
Q5_K_M
Q6_K
Q8_0

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.

Downloads last month: 2,356

GGUF

Model size

70.6B params

Architecture

llama

4-bit

5-bit

6-bit

8-bit

View +3 files

Inference Providers NEW

Text Generation

This model is not currently available via any of the supported Inference Providers.

Model tree for ddh0/L3.3-Electra-R1-70b-GGUF

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.3-70B-Instruct

Finetuned

EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0

Finetuned

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

Quantized

(6)

this model