ukisai/Swift1.5-Qwen3.8-Flash-Next
LoRA-style vs Qwen/Qwen3.8-Flash-Next. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/302, other 0/8, Attention 156/608, MLP 144/602, Embeddings 0/137, lm_head 0/1
18 derivatives checked
- ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF: Not comparable yet
- SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF: Not comparable yet
- slider-meister-pub/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF: Not comparable yet
- bartowski/ukisai_Swift-Qwen3.8-Flash-Next-GGUF: Not comparable yet
- taurusduan/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF: Not comparable yet
- taurusduan/Swift-1.5-Qwen3.8-Flash-Next-GGUF: Not comparable yet
- Baekpica/Swift1.5-Qwen3.8-Flash-Next-Mixed-Quant-GGUF: Not comparable yet
- tirex2001/Swift-1.5-Qwen3.8-Flash-Next-DACAN: Not comparable yet
- scottlowry/Swift1.5-Qwen3.8-Flash-Next-oQ4e-fp16-mtp: Quantization
- scottlowry/Swift1.5-Qwen3.8-Flash-Next-oQ4e-mtp: Quantization
- adriandj3/Swift-1.5-Qwen3.8-Flash-Next-MTP-for-GGUF-and-NVFP4: Not comparable yet
- tomngdev/Swift1.5-Qwen3.8-Flash-Next-GGUF: Not comparable yet
- Dankpaws/Swift1.5-Qwen3.8-Flash-Next-MLX-4.7bpw: Quantization
- nitinpanj/Swift-Qwen3.8-Flash-Next-Q4_0-Q8out-v3-GGUF: Not comparable yet
- scottlowry/Swift1.5-Qwen3.8-Flash-Next-oQ6e-mtp: Quantization
- scottlowry/Swift1.5-Qwen3.8-Flash-Next-oQ5e-mtp: Quantization
- scottlowry/Swift1.5-Qwen3.8-Flash-Next-oQ8e-mtp: Quantization
- ohmysimo/Wren: Partial fine-tune