Downloads · 30 days
22.1K
32% of all-time downloads
BattleGhost/Qwen3.8-Flash-Next-UNCENSORED-IQ2_XXS-GGUF
Qwen3.8-Flash-Next-UNCENSORED-IQ2_XXS-GGUF is a text generation model from BattleGhost. Use it when you need the model to write or continue text. It is set up for llama.cpp. The card lists the license as other.
IQ2XXS GGUF conversion of dealignai/Qwen3.8-Flash-Next-UNCENSORED-FP8, intended as a practical build for a system with 64 GB RAM and a 16 GB GPU.
Downloads · 30 days
22.1K
32% of all-time downloads
All-time downloads
68.2K
Public
Repo size
74.7 GB
Likes
8
Public
Click a slice to open those files.
.gguf74.7 GB · 100%
From the Hugging Face model README
IQ2_XXS GGUF conversion of
dealignai/Qwen3.8-Flash-Next-UNCENSORED-FP8, intended as a practical build for a system with 64 GB RAM and a 16 GB GPU.
This is the exact modified dealignai UNCENSORED checkpoint converted and quantized to GGUF. It is not derived from the independently modified OrcaRouter model.
| File | Size | SHA-256 |
|---|---|---|
Qwen3.8-Flash-Next-UNCENSORED-IQ2_XXS.gguf | 74,658,862,272 bytes (69.531 GiB) | c04bb625ee9a50aaf25d61d2cea8187934117f82bd41aa48918a0f03b37d4173 |
The unquantized BF16 GGUF is available separately at BattleGhost/Qwen3.8-Flash-Next-UNCENSORED-BF16-GGUF.
2d9a479fd8643c394f1602b4ef1c8757dda4c518c841aeeb8bb2fe417038dadfa9b007cf1a9ef950 (build b10687)qwen4expunsloth/Qwen3.8-Flash-Next-GGUFoutput_hc_down.weight: IQ4_NLtoken_embd.weight: Q4_KThe source checkpoint stores its PLE n-gram FP8 shards with one shared ngram_embedding.weight_scale. That scale was applied while producing the BF16 intermediate. Quantization did not restore or substitute the original Qwen weights.
Use a recent llama.cpp build containing Qwen3.8 / qwen4exp support. The relevant implementation was merged in ggml-org/llama.cpp#27742.
This is a format conversion and quantization of the dealignai checkpoint and remains governed by the Qwen Community License 1.0. Review the source model's license, model card, and disclaimer before use.
The source model has safety refusals removed. Users are responsible for complying with applicable laws and platform policies.