전체 검색

AI 모델 84759

• Huihui-Qwen3.8-27B-abliterated-NVFP4↗

  sakamakismile

  NVFP4 (W4A4, group 16) quantization of **huihui-ai/Huihui-Qwen3.8-27B-abliterated** — all credit for the model goes to @huihui-ai. This repo carries only the quantized weights. > ### 🔄 Re-quantized 2026-08-24 from the upstream *Latest update 3* > > Upstream narrowed the ablation to **layers 18–51 only** (previously everything from layer 15 up), leaving the rest of the network untouched, to retain more of the original model's performance. MTP and the vision tower are unmodified. > > I diffed the shards before re-baking: **6 of 18 changed**, and they are exactly the shards holding **layers 15–17 and 52–63**. The changelog matches the bits. > > **This is not a cosmetic update.** The `reasoning_effort: xhigh` thinking-runaway that the previous revision failed is **gone** — see the gotcha section. If you were pinning `medium` because of it, you no longer have to. > > The previous NVFP4 revision remains available at commit history / `revision=` if you need it. **Throughput** (TP=4 on RTX PRO 2000 Blackwell ×4, 32k ctx, KV fp8, MTP n=3, 512 tok fixed, `reasoning_effort: low`):

• codet5p-2b↗

  Salesforce

• Wizard-Vicuna-13B-Uncensored-GGUF↗

  second-state

• Laguna-M.1-GGUF↗

  sigargv

• 30B-Lazarus-GGUF↗

  TheBloke

• llama-2-70b-Guanaco-QLoRA-GGUF↗

  TheBloke

• Noromaid-20B-v0.1.1-GGUF↗

  TheBloke

• dla102.in1k↗

  timm

• repvit_m3.dist_in1k↗

  timm

• Ornith-1.5-35B-A3B-NVFP4-512K-GGUF↗

  TizzyT566