Tag
Explore by tags
A dynamically quantized GGUF build of Ornith-1.5-35B optimized for agentic code-fixing and multi-turn conversations: targets 4-bit/≈22GB deployments, includes a vision projector, a custom importance matrix and a concise chat template.
GGUF-quantized, refusal-removed build of Qwen3.8-Flash-Next for llama.cpp that provides multimodal (image+text), reasoning and tool-calling capabilities; released for security research and red-teaming under the Apache-2.0 license.
Provides per-tensor non-uniform GGUF quantizations of Qwen3.8-27B using GSQ and RCO, delivering high accuracy at 2.5–3.5 bits and including a BF16 vision projector for multimodal use. Optimized to run unmodified in llama.cpp, Ollama, and LM Studio.
A TURBO multi-stage fine-tune of Qwen3.8‑27B that shortens internal “thinking” token blocks and raises ARC benchmarks (8‑bit ARC‑C ≈735, ARC‑E ≈882). It ships GGUF quants (regular and MTP, Neo‑Imatrix), vision support and 256k context for local multimodal inference on consumer GPUs.
Provides per-tensor mixed-precision GGUF quantizations of the Qwen3.8-Flash-Next MoE model using GSQ (Gumbel-Softmax Quantization) to produce tensor-level quantized variants and RCO (Riemannian Constrained Optimization) to allocate quant types under exact size budgets; includes a BF16 vision projector and three size/bit-width operating points.
F16 GGUF release packaged for llama.cpp and similar runtimes that applies UkisAI's Swift adapter to Qwen3.8-27B. Cuts reasoning/thinking tokens by ~58% with <1% performance loss, includes multimodal projector, MTP layers, multiple GGUF quant tiers, and is distributed under the Swift Open License v1.0.
Provides compact mixed-precision GGUF quantizations of UkisAI's Swift 1.5 (derived from Qwen3.8-27B), using ISTA GSQ-RCO per-tensor allocations with Swift-specific refinement. Offers multiple 8–12 GB tiers, optional MTP heads, and KLD evaluation against the Swift BF16 baseline.
Provides a high-fidelity mixed-precision (≈3-bit) GGUF quant of Qwen3.8-27B tailored for long-horizon agent workloads and cyber-focused red-teaming. Preserves reasoning, thinking mode, MTP speculative decoding and vision (via a separate mmproj); released as an uncensored/abliterated research build under Apache-2.0.
Post-trained multimodal Qwen3.8-27B variant that uses alternating SFT and RLOO to reduce pathological long reasoning tails; ships multiple quantization tiers (BF16, FP8, NVFP4, INT8, INT4, GGUF), supports MTP and DFlash2 speculative decoding, and includes detailed benchmark and runtime recommendations.
GGUF (llama.cpp) quantized build of MiniCPM‑V 4.7 35B‑A3B for local/CPU and on-device multimodal image/video→text inference; supports imatrix mixed quantization, Lookahead Expert Scheduling and DSpark speculative decoding to reduce expert-loading stalls and improve throughput.
A drop-in GGUF text encoder (Qwen3‑VL‑8B‑Instruct) with its refusal direction projected out for use with stable-diffusion.cpp; drastically reduces chat refusals while leaving the 7B image denoiser and visual outputs essentially unchanged.