Filtering by: modelavailability · clear filter
GLM 5.3 Flash Uncensored is now available on NanoGPT and included in the subscription at 1x included-input usage.
This uncensored fine-tune combines efficient reasoning with fewer refusals for unrestricted chat, creative writing, coding, tool use, agentic work, and long-context tasks.
Try it:
https://nano-gpt.com/conversation?model=z-ai%2Fglm-5.3-flash-uncensored
Abliterated Model and Abliterated Model Large are now available on NanoGPT.
Abliterated Model supports text, images, structured output, and long-context work with a 262K context window. Abliterated Model Large is text-only, based on GLM-5.2, with a one-million-token context window for harder reasoning and long documents.
Try them:
https://nano-gpt.com/conversation?model=abliteration-ai%2Fabliterated-model
https://nano-gpt.com/conversation?model=abliteration-ai%2Fabliterated-model-large
Qwen 3.8 Flash Next is now available on NanoGPT and included in the subscription at 1x included-input usage.
This fast multimodal reasoning model supports text, images, and video with a 1M-token context window. It is built for coding, long documents and codebases, agent workflows, visual understanding, tool use, structured output, and long-video analysis.
Try it:
https://nano-gpt.com/conversation?model=alibaba%2Fqwen3.8-flash
GLM 5.3 Flash is now available on NanoGPT and included in the subscription at 1x usage.
Previously tested anonymously as ox-alpha, this open-weight, natively multimodal 320B reasoning model activates 18B parameters per token. It is built for efficient coding, long-running agent tasks, visual understanding, tool use, and precise long-context work.
Try it:
https://nano-gpt.com/conversation?model=z-ai%2Fglm-5.3-flash
Qwen 3.8 27B Obliterated and its Thinking variant have replaced Qwen 3.8 27B Uncensored on NanoGPT.
The stronger LoRA-tuned model is designed for fewer refusals across creative work, coding, reasoning, tool use, image understanding, and long-context tasks. Both remain included in the subscription at 1x usage.
Try it:
https://nano-gpt.com/conversation?model=qwen%2Fqwen3.8-27b-obliterated
Qwen3.8 27B TEE is now available!
This private open-weight 27B multimodal model runs inside a Trusted Execution Environment with attestation support. It handles text, images, and video across a 262K context window and is built for reasoning, coding, tool use, structured output, and long-running professional workflows.
Try it:
Wan 3.0 Prime is now available! Create cinematic videos from a text prompt, animate a start image with optional end-frame guidance, or use images, videos, and audio as references to preserve characters, products, voices, motion, and visual style across a shot. One unified model automatically chooses the right generation mode from your inputs and can generate synchronized audio with the finished clip.
Try it:
https://nano-gpt.com/media?mode=video&model=alibaba%2Fwan-3.0-prime
Gemma 4 26B A4B Uncensored is now available on NanoGPT and included in the subscription at 1x included-input usage!
This open-weight multimodal mixture-of-experts model is tuned for fewer refusals across chat, coding, tool use, image understanding, and long-context work.
Try it:
https://nano-gpt.com/conversation?model=google%2Fgemma-4-26b-a4b-uncensored
Qwen 3.8 27B Uncensored is now available on NanoGPT and included in the subscription at 1x usage.
This open-weight FP8 model is tuned for fewer refusals across chat, coding, tool use, image understanding, and long-context work.
Try it:
DeepSeek V4 Flash Vision Exp is now available on NanoGPT and included in the subscription at 1x usage.
It adds image understanding while retaining reasoning, coding, tool use, agent capabilities, and a 1M-token context window.
Try it: