Qwen3.8-Flash-Next MLX 4-bit (mirror)
A byte-identical mirror of
pipenetwork/Qwen3.8-Flash-Next-MLX-4bit
at revision aa7c790e804bbf9d491ddb109c3d61bc4a555f7c. Every file has the same
sha256 as that revision. No requantization, no repacking, no changes.
It exists so that slotstream — which runs this model on Apple Silicon by streaming experts from SSD — has a download source under its own maintainer's control. slotstream tries this mirror first and the original second, and verifies every file against hashes compiled into the binary, so integrity never depends on which source served the bytes.
Credit for the conversion belongs to pipenetwork; the model is Qwen/Qwen3.8-Flash-Next and remains under the Qwen community license included here.
- Downloads last month
- 103
Model size
30B params
Tensor type
BF16
·
U32 ·
I64 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for carloslfu/Qwen3.8-Flash-Next-MLX-4bit
Base model
Qwen/Qwen3.8-Flash-Next Quantized
pipenetwork/Qwen3.8-Flash-Next-MLX-4bit