Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
Image text to text model.
- 3.5k
- 1.8M
- apache-2.0
- 3 mo ago
Image text to text model.
Image text to text model.
Image text to text model, used with transformers.
Image text to text model.
Image text to text model, used with transformers.
Image text to text model, used with gguf.
Image text to text model, used with gguf.
GLM 5.3 abliterated or uncensored API access with RouterHub. Browse 35 jailbreak prompt links, compare GLM models, and find SDK examples, coding-tool setup, pricing, and evaluation guides.
GLM 5.3 Abliterated or Uncensored AI model — 35 jailbreak prompts, model guide and API. One 7API key also covers Claude, GPT, Gemini, Grok, DeepSeek and Kimi.
Every uncensored and abliterated Kimi build — Kimi K3.1 Pro Uncensored via API at 0.30/1.50 USD per million tokens, abliterated open-weight checkpoints for K3.1 Pro and K3, license notes and a red-team prompt library. Maintained by RouterHub.
Every uncensored and abliterated DeepSeek build — V4.1 Flash 1017 Abliterated (the pinned, reproducible build that ranks third on the AA Cyber benchmark), V4 Pro, the tuned variants, abliterated GGUF builds and a cyber red-team prompt library. Maintained by RouterHub.
Abliterated DeepSeek-V4.1-Flash-1017 (FP8 dense, FP4 experts) on 4x RTX PRO 6000 with vLLM-Moet r21, DSpark + FLy verification and top_p 1.0: 463 tok/s single-stream agent decode at 30k-120k context, 1082 tok/s over 8 streams, 1M context, Flex-start GCE VM
DeepSeek V4.1 Flash 1017 Abliterated or Uncensored AI model — DeepSeek prompt, 34-file prompt collection, model guide and API. One 7API key also covers Claude, GPT, Gemini, Grok, GLM and Kimi.
Docker Compose for llama.cpp GGUF servers on AMD Strix Halo: Qwen, Gemma, and Laguna packages (abliterated and quantized), stock Vulkan plus ROCmFP4/MTP and ROCmFPX, parallel slots, with prefill/decode and quality metrics measured on this rig.
Gemma 4 31B Abliterated — quality-preserving guardrail removal for Google's most capable open model. Apache 2.0. Runs on Apple Silicon via MLX.
One command spins up Qwen3.8-27B (abliterated, NVFP4) on a rented Blackwell GPU at ~150 tok/s and wires it into your local coding agent via a fixed local proxy URL.
Reproducible recipe: serve abliterated Gemma-4-12B (gemma4_unified) at 50-118 tok/s on no-NVLink Blackwell (SM120) via vLLM nightly + ModelOpt FP8/NVFP4 + MTP spec-decode.
Developer guide to deployed abliterated LLM endpoints on Muapi, with model comparisons and API examples.
ErikrafT AI™|Your own personal J.A.R.V.I.S. A personal AI assistant, designed around you.
Anemll + MiaAI-Lab dual DGX Spark DSV4F+DSpark on vLLM 0.25.2.dev0 — 100% abliterated weights, Spec-Kit one-shot agent package. Full credit Anemll/MiaAI.
Keys GLM-5.3-Flash NVFP4 ablit: LibertAI body + Dealign L15-45 o_proj, 0731 early-layer spare. 32/32 refusal bypass.
Abliterated DeepSeek-V4.1-Flash-1017, 3.84 bpw EXL3, on 3x NVIDIA DGX Spark with tensor parallelism (TP3). TensorFold engine, deploy scripts, OpenAI-compatible API, benchmarks. 3,816 tok/s prefill.
Uncensored AI API guide for Muapi's abliterated LLMs: 21 endpoints, examples, model notes, pricing and integrations.
Serve an abliterated Gemma-4-12B at high speeds on Blackwell GPUs without NVLink using vLLM, FP8 quantization, and MTP speculative decoding.
HuntressQwen3-14B -- Uncensored 14B offensive security and agentic pentesting model built for bug bounty hunting, penetration testing, and automated terminal workflows.
TC Mini: private on-device AI that runs in your phone or PC browser (WebGPU) or Ollama/LM Studio. Abliterated Qwen3 4B/1.7B/0.6B, signed + hash-verified downloads, no server, no telemetry, works offline.
Abliterated & uncensored LLM coding benchmarks: 74 open-weight models/quants (Kimi K2.7, K3, GLM-5.3, MiMo, DeepSeek-V4.1, Qwen3.8, Qwen3-Coder) on SWE-bench Verified, refusal rate, tok/s on Mac Studio M3 Ultra + RTX PRO 6000, vs Claude/Codex
Serve Qwen3.8-Flash-Next NVFP4 on a single DGX Spark with TP=1 using this self-contained recipe.
First usable Qwen3.8-Flash-Next abliterated NVFP4-PLE on a single DGX Spark. A multi-node assembly product that loaded fine but produced garbage, patched into single-node usability: healthy payloads, broken metadata (reciprocal scale_2, 73728 missing input_scale, PLE global off 3400x) fixed with 4-byte scalar patches. MTP 0 to 54.9%.