Qwen 3.5 — quantized - a majentik Collection

majentik 's Collections

UEmbed — multimodal embeddings (MLX, dense text)

Meta Muse Glimmer — MLX

Embeddings (ONNX)

Nemotron — quantized

Verified MLX releases (smoke-gated)

gpt-oss — rebuilt GGUFs

OCR & Document AI (MLX)

ASR on Apple Silicon (MLX)

MERaLiON — Singapore speech models on MLX

Qwen 3.5 — quantized

Qwen 3.6 — quantized

Gemma 4 — quantized (GGUF + MLX)

Qwen 3.5 — quantized

updated about 16 hours ago

Quantized GGUF and MLX packs of the Qwen 3.5 model family, including the 397B-A17B MoE.