NVIDIA Releases High-Efficiency 'FP4' Quantized Model for Qwen3.8 Flash Next
NVIDIA has officially released an FP4 quantized version of Qwen3.8 Flash Next on Hugging Face, significantly shrinking model weights while maintaining near-loss
#Qwen3.8
TAU-HOME.COM stories tagged Qwen3.8.
Swift 1.5 GSQ-RCO GGUF Release Packs 27B-Class Qwen3.8 for 16GB GPUs
UkisAI's reasoning-efficient Swift 1.5 Qwen3.8-27B gets an ultra-light 2-3-bit GSQ-RCO GGUF packaging for llama.cpp, plus IQ3_S 16GB benchmark reports.
Qwen3.8-Flash-Next NVFP4 Benchmarked on Single DGX Spark: 1M Context with FP8 KV Cache
A benchmark of Qwen3.8-Flash-Next NVFP4 on a single 128GB DGX Spark demonstrates 1M context with FP8 KV cache, 4-stream concurrency, and full multimodal input s
Mitsuba & HiMitsuba 27B GGUF: A 1.58-Bit Vision-Language Model for ComfyUI on 16GB GPUs
Mitsuba and its uncensored HiMitsuba LoRA compress Qwen3.8-27B into a 7.3GB 1.58-bit VLM, enabling fast local image analysis and prompt generation for ComfyUI o
Rapid-MLX v0.15.4: Qwen3.8-27B TensorFold and DFlash2 Speculative Decoding on Apple Silicon
Apple Silicon local LLM engine Rapid-MLX v0.15.4 adds an experimental TensorFold profile with DFlash2 speculative decoding for Qwen3.8-27B alongside MTP acceler
Bonsai 2 27B: 5.95GB Ternary Model Gets Weight-Level Refusal Abliteration CRACK Build
The dealignai team has released a weight-level abliterated CRACK build of PrismML's 5.95GB ternary Qwen3.8-27B model Bonsai 2, eliminating refusal behavior with
PrismML Launches Bonsai 2, a 27B-Class Ternary Model Compressed 9x
Based on Qwen3.8 27B, PrismML has launched Bonsai 2 27B, a new flagship Ternary model compressed to 5.9GB with minimal performance loss.