Qwen/Qwen3.6-35B-A3Bcontinue pretrain -> instruction SFT -> preference tuning (DPO/GRPO) -> eval + distill.
The in-app runner handles continued pretrain, SFT, and GRPO. DPO and full distillation recipes are generated below for external stacks.
QwenLM/Qwen3.6
HF: Qwen/Qwen3.6-35B-A3B
Default lane: AGI-POC + Unsloth
Loading hardware info...
| ID | Base | Type | Date | |
|---|---|---|---|---|
| Loading... | ||||
Run a reusable eval suite against one or two models. This compares pass rates on the suite's cases; use Manage suites to add test cases and grading rules.
| Format | Use Case |
|---|---|
| GGUF Q4_K_M | llama.cpp, Ollama, LM Studio |
| GGUF Q8_0 | High quality CPU inference |
| Merged 16-bit | Full precision safetensors |
| LoRA only | Adapter weights (smallest) |
| UD-Q5_K_XL | Unsloth Dynamic (best ratio) |