Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Qwen3.6-35B-A3B-oQ4e-mtp – AI Model by mkreynolds | AlphaNeural AI
You can deploy this model and start earning money today!
mkreynolds
/
Qwen3.6-35B-A3B-oQ4e-mtp
like
0
mlx
safetensors
qwen3_5_moe
oq
quantized
Qwen/Qwen3.6-35B-A3B
quantized
4-bit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Qwen3.6-35B-A3B-oQ4e-mtp
This is a 4-bit-precision dynamic quantization of Qwen3.6-35B-A3B with imatrix weighting, quantized using
oQe
(oMLX v0.5.1). MTP weights are preserved; use oMLX Lightning MTP.
Quantization details
Model type
: qwen3_5_moe
Bits
: 4
Group size
: 64
Format
: MLX safetensors
