ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF
Not comparable yet vs Qwen/Qwen3.8-Flash-Next. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (518 of 1658/1224 match), usually an architecture llama.cpp's name map doesn't cover yet.
12 derivatives checked
- SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF: Partial fine-tune
- alesha-pro/Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata-GGUF: Identical copy
- 0xSojalSec/Qwen3.8-Flash-Next-Uncensored-GSQ-RCO-12-GB-GPU: Partial fine-tune
- KilltheSniper/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF: Partial fine-tune
- NovaeonStudio/Qwen3.8-Flash-Next-GSQ-RCO-Q2-mlx: Quantization
- DarkKitsune/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-PLE-50pct: LoRA-style
- ScottzillaSystems/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF: Partial fine-tune
- KENIC-1/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF: Partial fine-tune
- webmp3/Sakura-Qwen3.8-Flash-Next-ISTA-3bit-352E-GGUF: Quantization
- arytekSI/Qwen3.8-Flash-Next-Abliterated-GSQ-RCO-IQ3_XXS-Calibrated-GGUF: Partial fine-tune
- peasantsmith/qwen38-flash-next-v100-recipe: Full fine-tune
- KENIC-1/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF-IQ3_XXS: Partial fine-tune