Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer

Qwen / Qwen3.6-27B

QUANTIZED BY: UnstableLlama

Information

exl3 quantization of Qwen3.6-27B via exllamav3.
repo generated automatically with ezexl3.

Repo Data

REVISION	GiB	KL DIV	PPL
2.06bpw	10.01	0.2420	8.890
3.08bpw	12.90	0.0560	7.5790
4.15bpw	15.92	0.0162	7.3602
6.00bpw	21.17	0.0040	7.4181
8.00bpw	27.13	0.0004	7.3799
bf16	51.75	0.0000	7.3867

SVG Catbench

2.06 bpw	3.08 bpw	4.15 bpw	6.00 bpw
8.00 bpw

CLI Download

hf download UnstableLlama/Qwen3.6-27B-exl3-2.06bpw --local-dir ./Qwen3.6-27B-exl3-2.06bpw

Safetensors

Model size

5B params

Tensor type

BF16

F16

I16

Inference Providers NEW

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

Model tree for UnstableLlama/Qwen3.6-27B-exl3-2.06bpw

Base model

Quantized

(715)

this model