サイト内検索

AI モデル 84759

• Qwen3.5-9B-GRPO-ifeval-v0-think-step400↗

  ConnorYU

• madlad400-3b-ct2-int8↗

  cstr

• Gemma-The-Writer-N-Restless-Quill-10B-Uncensored-GGUF↗

  DavidAU

  Refreshed, Upgraded and New quants (augmented). Better performance for all quants (see below). And link to new float 32 remastered version. This is a Gemma2 model merge of the top FOUR storytelling / writing models as noted at EQBench, tuned specifically for fiction, story, and writing. It also contains "gemma2-gutenberg", "Tiger-Gemma" (uncensor) and "Ellaria" (uncensor some more) to give it a unique prose style.

• Qwen3.8-27B-UNCENSORED-GGUF↗

  dealignai

  Uncensored vision-language reasoning model · GGUF for llama.cpp · vision + video + MTP in every quant dealign.ai **Qwen3.8-27B-CRACK** is a CRACK-abliterated build of Qwen3.8-27B — a native **vision-language hybrid** (GatedDeltaNet linear-attention + full attention) with refusal behavior removed. Knowledge, multi-step reasoning (low / medium / xhigh), coding, and image/video understanding are preserved. Every quant ships with the **vision projector** and the **native Multi-Token-Prediction (MTP) head**. > ⚠️ Research artifact with reduced safety guardrails. It will follow instructions a stock model declines. > Intended for research and authorized red-teaming. You are responsible for lawful use.

• Gmcoder↗

  emperorofrome

  **gmcoder** is a 9B merged coding model developed with support from **Galactic Mandate Linux**. It is intended for code generation, debugging, explanations, and algorithmic problem solving. The reported HumanEval+ Mini result is competitive with the compared 9B coding models. On a separate internal knowledge and reasoning benchmark suite, gmcoder scored 30% higher than Qwen3.5-9B and Ornith-1.5-9B. Each model received one greedy completion per task at temperature 0. The run used EvalPlus 0.4.0.dev2 and all 164 HumanEval tasks. The gmcoder and internal comparator entries are Q8_0. The numbers are pass@1; HumanEval+ requires passing both the original and augmented tests. This is a 164-task, single-sample comparison. Oxcoder's HumanEval/132 response was manually skipped after it stopped progressing; a blank answer was scored as a failure, but the cause of that non-completion was not recorded. The internal comparator returned two empty answers; both counted as failures. These results measure short coding problems, not repository-level or agent performance.

• chameleon-7b↗

  facebook

• dan-latn-100mb-after-ppt-mp-struct-100mb-ckpt500_seed455↗

  francesca9805

• Fwizzer-R1-3B-RU-v2↗

  fwizzer1

• paligemma-3b-ft-ocrvqa-896-jax↗

  Google

• EliteReplay-BIRD-4B↗

  hananour