Downloads · 30 days
15
9% of all-time downloads
companion-3.5-4b-mlx
wyrdsekai/companion-3.5-4b-mlx
companion-3.5-4b-mlx is a text generation model from wyrdsekai. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
MLX 4-bit conversion of the Wyrdsekai companion voice base, for Apple Silicon hosts. Pulled automatically by wyrd setup on macOS (arm64) when the MLX voice runtime is bootstrapped; serves on :8201 via mlxlm.server.
All-time downloads
175
Public
Parameters
4.2B
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 GB · 99%
Parameter types
How the weights are stored.
U324.2B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Wyrdsekai Qwen3.5-4B v10 (MLX 4-bit)
MLX 4-bit conversion of the Wyrdsekai companion voice base,
for Apple Silicon hosts. Pulled automatically by wyrd setup on macOS (arm64) when the MLX
voice runtime is bootstrapped; serves on :8201 via mlx_lm.server.
GGUF equivalent for llama.cpp hosts: wyrdsekai/companion-3.5-4b-gguf. Training data: synthetic corpora only (no user conversations).
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Languages
- en, es, ja
- Created
- Jun 11, 2026
- Updated
- Jul 30, 2026