Provides a full GGUF quant ladder of an "abliterated" Qwen3.8-27B for local llama.cpp inference — includes every K-quant, embedded MTP speculative head, and optional vision projectors; refusal behavior was reduced at the weight level, so validate before production.
A 9B-parameter distillation that transfers chain-of-thought reasoning from Qwen3.8 into the Qwen3.5-9B architecture for single‑GPU deployment; trained on ~70,000 teacher traces, it offers 262k-token context, native function-calling, and improved MMLU performance.
An FP8-quantized, uncensored mirror of Qwen3.8-27B for image-text-to-text tasks — preserves native multimodal vision and very long context while targeting transformers/vLLM deployments; intended for offline testing and red-teaming and may bypass built-in safety filters.
A Gated-DeltaNet-aware mixed-precision GGUF quantization of Qwen3.8-27B for efficient local inference; preserves the MTP draft head and offers an optional BF16 mmproj for images. Weights are ~11.73 GiB (3.69 bpw), sized for 16–24 GB GPUs at modest context.
An uncensored fork of Qwen3.8-27B that removes refusal/safety filters via an “abliteration” technique while preserving the first 15 layers and multimodal capabilities; intended for controlled research and testing rather than production.
Local GGUF build of Qwen 3.8 27B with the refusal direction ablated for llama.cpp; includes vision projector (mmproj), MTP speculative head, a 262k context window and multiple quant tiers (Q2–Q8, F16). Research-only release that requires updated llama.cpp and explicit safety layers.
An uncensored, "abliterated" fork of Qwen3.8-27B that removes refusal behavior by modifying targeted weights and provides multiple GGUF/BF16 quantized variants for local research and deployment, while carrying significantly reduced safety filtering.
Provides quantized GGUF variants of Qwen3.8-27B with an 'Aggressive' uncensoring profile and an optional HauhauCS FastMTP sidecar to accelerate MTP speculative decoding; includes a BF16 vision projector and K_P quant levels for VRAM/quality trade-offs.
Post-trained Qwen3.8-27B variant using the COLD FUSION (GAIN+Unsloth) tuning to reduce internal reasoning-token use and improve instruction following while keeping base capabilities. Deliverables include 256k-context-compatible GGUF quants (regular and MTP, NEO IMATRIX), vision support via an mmproj, and three reasoning-effort modes (xhigh/medium/low).
Provides a quantized MLX conversion of Qwen3.8-27B for Apple Silicon (2/4/6/8-bit) with the model's refusal-direction ablated, preserving multimodal vision+text capability; intended for red‑teaming, interpretability and safety research, not unmoderated production use.
Presents a unified black-box reinforcement learning framework to train and optimize agents running inside complex execution harnesses. Uses sandbox-parallel rollouts, a serving proxy that captures model calls and reconstructs multi-turn trajectories as prefix trees, and adapted GRPO/PPO optimizers to achieve stable, scalable RL across heterogeneous harnesses.
Enables interactive serving of large Mixture-of-Experts (MoE) models on personal machines by adapting offload and execution to measured device bandwidth and agentic workload patterns. Key features include bandwidth-adaptive execution, semantic-aware caching of recurrent state, and an elastic GPU expert cache; supports 20+ MoE models and runs models from ~35B to 753B on consumer/workstation GPUs.