Shinrali/Qwen3.8-Flash-Next-NVIDIA-Hybrid-Single-Spark
LoRA-style vs nvidia/Qwen3.8-Flash-Next-NVFP4. 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: Embeddings 0/138, MLP 144/1613, Attention 156/608, Norms 0/302, other 0/8, lm_head 0/1
1 derivatives checked
- Shinrali/Qwen3.8-Flash-Next-NVIDIA-Hybrid-FP8-LMHead-Single-Spark: Partial fine-tune