marcelone
/

Jinx-Qwen3-4B-gguf

Model card Files Files and versions

Recommended

Jinx-Qwen3-4B-gguf-q6_k-q-8 (mixed-precision): selected weights (output, token embeddings, attention/FFN layers in first and last blocks) quantized to Q8_0, remaining tensors Q6_k, reducing memory footprint while preserving inference fidelity.

Downloads last month: 552

GGUF

Model size

4.02B 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-Qwen3-4B-gguf

Base model

Qwen/Qwen3-4B-Base

Finetuned

Finetuned

Jinx-org/Jinx-Qwen3-4B

Quantized

(1)

this model

Collection including marcelone/Jinx-Qwen3-4B-gguf

Uncensored Models - RTX 3060 12 GB

6 items • Updated 6 days ago