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

>> coder3101 / Qwen3.5-122B-A10B-heretic-v2

[QUANTS BY :: UnstableLlama]

// Information

exl3 2.08 bpw quantization of coder3101's Qwen3.5-122B-A10B-heretic-v2 via exllamav3.

Repo generated automatically with ezexl3.

// Repo Data

REVISION	GiB	KL DIV	PPL
2.08bpw	32.323	0.3001	5.1166
4.06bpw	60.390	0.0317	4.8333
bf16	228.296	0.000	4.791

// CLI Download

hf download UnstableLlama/Qwen3.5-122B-A10B-heretic-v2-exl3-2.08bpw/ --local-dir ./UnstableLlama/Qwen3.5-122B-A10B-heretic-v2-exl3-2.08bpw/

Safetensors

Model size

17B params

Tensor type

F16

I16

BF16

Inference Providers NEW

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

Model tree for UnstableLlama/Qwen3.5-122B-A10B-heretic-v2-exl3-2.08bpw

Base model

Finetuned

Quantized

(9)

this model