marcelone
/

Jinx-Qwen3-8B-gguf

Model card Files Files and versions

Weight Types

OE
output.weight, output_norm.weight, token_embd.weight -> BF16

OE32
output.weight, output_norm.weight, token_embd.weight -> F32

Downloads last month: 2,007

GGUF

Model size

8.19B params

Architecture

qwen3

Hardware compatibility

Log In to view the estimation

4-bit

6-bit

8-bit

16-bit

32-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for marcelone/Jinx-Qwen3-8B-gguf

Base model

Qwen/Qwen3-8B-Base

Finetuned

Finetuned

Jinx-org/Jinx-Qwen3-8B

Quantized

(1)

this model