You can deploy this model and start earning money today!

fritskarl/
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-text-oQ4e-mtp

Model type: qwen3_5_moe
Bits: 4
Group size: 64
Format: MLX safetensors

Name: Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-text-oQ4e-mtp
Availability: InStock

Views

No views yet

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-text-oQ4e-mtp

NOTE: This is an oQ4e quantized version, including mtp and text only (no vision adapter) of the original model found here.

This model was quantized using oQ (oMLX v0.5.0.dev3) mixed-precision quantization.