Downloads · 30 days
198
14% of all-time downloads
Qwen3.8-Flash-Next-MLX-4bit
carloslfu/Qwen3.8-Flash-Next-MLX-4bit
Qwen3.8-Flash-Next-MLX-4bit is a machine learning model from carloslfu. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as other.
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.
All-time downloads
1.4K
Public
Parameters
177B
145 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors105 GB · 100%
Parameter types
How the weights are stored.
U32177B · 100%
Base models
Model card
From the Hugging Face model README
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.
- Library
- mlx
- Type
- qwen4_exp
- License
- other
- Created
- Aug 29, 2026
- Updated
- Sep 6, 2026