empero-ai/Qwen3.8-35B-A3B-Distill
Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 94% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 0/5, Attention 190/392, MLP 200/399, Norms 0/247, lm_head 0/1, other 0/1
23 derivatives checked
- empero-ai/Qwen3.8-35B-A3B-Distill-GGUF: Same weights, converted
- IsValorum/Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF: Not comparable yet
- MrFuzzihead/Qwen3.8-35B-A3B-Distill-APEX-GGUF: Not comparable yet
- IsValorum/Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-GGUF: Not comparable yet
- mradermacher/Qwen3.8-35B-A3B-Distill-i1-GGUF: Quantization
- mradermacher/Qwen3.8-35B-A3B-Distill-GGUF: Quantization
- SkyIsNotGreen/Scion-35B-A3B: Quantization
- NovaeonStudio/Qwen3.8-35B-A3B-Distill-oQ8-fp16-mtp: Quantization
- ngquocvinh/Qwen3.8-35B-A3B-Distill-GGUF: Quantization
- IsValorum/Qwen3.8-35B-A3B-Distill-MLX-APEX-MiniPlus-Abliterated: Quantization
- IsValorum/Qwen3.8-35B-A3B-Distill-MLX-APEX-NanoPlus-Abliterated: Quantization
- funnygeeker/Qwen3.8-35B-A3B-Distill-oQ6e-mtp: Quantization
- NovaeonStudio/Qwen3.8-35B-A3B-Distill-Heretic-oQ4-fp16-mtp: Quantization
- funnygeeker/Qwen3.8-35B-A3B-Distill-oQ6e-fp16-mtp: Quantization
- nvythong/Qwen3.8-35B-A3B-Distill-mlx-8Bit: Quantization
- NovaeonStudio/Qwen3.8-35B-A3B-Distill-Heretic-oQ8-fp16-mtp: Quantization
- nvythong/Qwen3.8-35B-A3B-Distill-mlx-4Bit: Quantization
- k9menor/1_Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-GGUF: Not comparable yet
- nvythong/Qwen3.8-35B-A3B-Distill-mlx-2Bit: Quantization
- NovaeonStudio/Qwen3.8-35B-A3B-Distill-Heretic-oQ6-fp16-mtp: Quantization
- nvythong/Qwen3.8-35B-A3B-Distill-mlx-fp16: Partial fine-tune
- qualitymaterial/Qwen3.8-35B-A3B-Distill-NVFP4-FreeToken: Quantization
- k9menor/0_Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-GGUF: Not comparable yet