전체 검색
AI 모델 84759
- OrcaRouter-Qwen3.8-Flash-Next-Uncensored-NVFP4-GPTQ-Strata↗
Maximilian228
> [!WARNING] > **Withdrawn from Strata NVFP4's installer (2026-10-10): as an agent, this abliterated build is much worse than the > original Qwen.** > - **A multi-step Claude Code task** (building an interactive 3D page), same prompt on both models: the original > Qwen3.8-Flash-Next (our GPTQ of it) > ran 175 steps, checking and fixing its work from screenshots, and gave a clearly better result. This build > stopped after 10-70 steps (3 runs) and declared the work done. > - **It closes its thinking sooner.** Over 7,869 positions of the original model's thinking (teacher-forced), this > pack raises the probability of ` ` by +0.12 nats on average. > - On a captured 72K-token Claude Code request (5 greedy runs each) it thought 997 tokens on average, the original > 1,699. > - Its style of thinking is the same; it just stops earlier. > - The likely cause is OrcaRouter's weight edit: it removes the refusal direction from all 149 residual-writing > matrices of every layer, including the late layers whose edit pushes ` `. > - **What the installer offers instead.** From Strata NVFP4 0.1.41-nvfp4.5: > - the original Qwen (`--family qwen-nvfp4-gptq`), with an opt-in switch (`--uncensored on`, off by default); > - the switch removes refusals at run time, in layers 8-33 only, and leaves the weights untouched; > - with thinking on it refused 0 of 104 English and 0 of 30 Ukrainian held-out harmful requests; > - ` ` +0.02 nats; thinking length as the original's. > > An existing install of this model keeps working, and the files here are unchanged. **Installer:** Strata NVFP4 v0.1.41-nvfp4.1 to .4 listed this repository as `--family orca-nvfp4` (the default from .3). From v0.1.41-nvfp4.5 the installer no longer offers it (see the warning above). To run this model by hand, see Run it. - **Chain:** `Qwen/Qwen3.8-Flash-Next` → `orcarouter/Qwen3.8-Flash-Next-Uncensored` (abliteration, BF16) → this quantization. - **Same size and the same decode cost as the ModelOpt NVFP4 experts** (63.3 GiB, 4.5 bits a weight), about **33% of their error** on held-out tokens: the same format, other codes and scales. - End to end, an earlier build of the same recipe (2026-10-02, the fork's docs/NVFP4.md) had a median per-answer KL of 0.0070 against an all-Q8_0 reference where ModelOpt's experts had 0.0107 (65%), better in 12 of 12 prompts. This build was checked as described under Checks, not re-
- Sailor2-1B-Chat-GGUF↗
MaziyarPanahi
- qwen-image-edit-2511-mflux-q5↗
mflux-community
- Qwen3-Coder-Next-8bit↗
mlx-community
- Qwen3-TTS-12Hz-1.7B-VoiceDesign-4bit↗
mlx-community
This model was converted to MLX format from `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` using mlx-audio version **0.3.0**.
- control_v1p_sd15_qrcode_monster↗
monster-labs
This model is made to generate creative QR codes that still scan. Keep in mind that not all generated codes might be readable, but you can try different parameters and prompts to get the desired results. Introducing the upgraded version of our model - Controlnet QR code Monster v2. V2 is a huge upgrade over v1, for scannability AND creativity. As with the former version, the readability of some generated codes may vary, however playing around with parameters and prompts could yield better results.
- ChatAllInOne-Yi-34B-200K-V1-i1-GGUF↗
mradermacher
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
- DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED-i1-GGUF↗
mradermacher
- EVA-abliterated-TIES-Qwen2.5-14B-i1-GGUF↗
mradermacher
- G4-Starry-Ocean-12B-GGUF↗
mradermacher