从语言到影像，从开源到 API。读懂模型能力、比较真实成本，
为你的下一个想法，找到合适的智能引擎。
Built from ornith-ai's original weights with our own importance matrix. The calibration corpora behind our builds are public. You can now run Ornith in Atomic Chat . See our quantization analysis below for measurements and instructions. Every number below is measured, not estimated. How we measured it is at the bottom, and the raw logs are in the metrics repo so you can check any of it yourself.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Built from Ornith's original weights with our own importance matrix. The calibration corpora and raw eval logs behind this card are public. See our quantization analysis below for measurements and instructions. You can now run Ornith 1.5 in Atomic Chat with toggles for thinking. GGUF builds of ornith-ai/Ornith-1.5-35B-A3B, converted and measured by AtomicChat.
译文排队中 · 当前显示来源原文
Built from Ornith's original weights with our own importance matrix. The calibration corpora and raw eval logs behind this card are public. Learn how to run Ornith 1.5 9B locally - read our guide . You can now run Ornith 1.5 in Atomic Chat with toggles for thinking. See our quantization analysis below for measurements and instructions. GGUF builds of ornith-ai/Ornith-1.5-9B, converted and measured by AtomicChat.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
The 8-step Qwen-Image-2.1 as GGUF for stable-diffusion.cpp, built from the published BF16 weights with our own importance matrix. The renders and measurements behind this card are public. Generate images locally in Atomic Chat . It runs stable-diffusion.cpp, the engine these files were built and checked with. Turbo drifts from the original picture faster than you might expect at 4 bits and below. Our AD-Q4_K stays 21% closer to the BF16 image than the plain Q4_K , for 150 MB more. Turbo needs its own 8-step schedule at CFG 1. The exact settings are in Running it . Looking for uncensored? The open Qwen-Image pipeline has no content filter. Qwen-Image-2.1-Turbo-Uncensored-GGUF removes the refusal direction from its text encoder. On images that changed nothing we could measure, and the card shows why. Each file renders the same 48 prompts × 2 seeds from the same starting noise as the BF16 weights. We compare every image with the BF16 image of the same prompt and seed.
译文排队中 · 当前显示来源原文
Qwen-Image's text encoder, Qwen3-VL-8B-Instruct, with its refusal direction projected out: a drop-in --llm for stable-diffusion.cpp next to our Turbo denoiser GGUFs . Below, exactly which part is uncensored and what that does to the pictures. The measurements are public. As a chat model, the encoder's refusals fall from 88.9% to 1.2% on held-out English prompts. MMLU is unchanged: 77.35% before and after. On images it changes nothing we could measure. The stock Qwen-Image pipeline has no filter and already draws all 9 sensitive categories we tested, and with this encoder not one of 45 prompts changed outcome. See where exactly this is uncensored . Generate images locally in Atomic Chat . It runs stable-diffusion.cpp, the engine these files were built and checked with. Qwen-Image 2.1 makes a picture with three parts. Only one of them is changed here.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
**Qwen3 4B Dflash b16**, self-quantized to GGUF by Atomic Chat. Built straight from Z Lab's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline. - **0.5B parameters**: the weights this repo quantizes. - **Context length**: 40,960 tokens (40K), as published by Z Lab. - **5 layers**: Dense decoder. - **Full imatrix ladder**: every quant is calibrated with an importance matrix. > [!NOTE] > These GGUFs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.
译文排队中 · 当前显示来源原文
**Qwen3.5 4B Dflash**, self-quantized to GGUF by Atomic Chat. Built straight from Z Lab's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline. - **0.6B parameters**: the weights this repo quantizes. - **Context length**: 262,144 tokens (256K), as published by Z Lab. - **6 layers**: Dense decoder, hybrid sliding-window (4096) and global attention. - **Full imatrix ladder**: every quant is calibrated with an importance matrix. > [!NOTE] > These GGUFs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.
译文排队中 · 当前显示来源原文
**Qwen3.5 4B**, self-quantized to GGUF by Atomic Chat. Built straight from Qwen's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline. > [!NOTE] > These GGUFs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model. > [!IMPORTANT] > Always pass `--jinja` so the **Qwen3.5 4B chat template** is applied. Without it the model can emit malformed turns.
译文排队中 · 当前显示来源原文
**Qwen3.5 9B Dflash**, self-quantized to GGUF by Atomic Chat. Built straight from Z Lab's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline. - **1.3B parameters**: the weights this repo quantizes. - **Context length**: 262,144 tokens (256K), as published by Z Lab. - **6 layers**: Dense decoder, hybrid sliding-window (4096) and global attention. - **Full imatrix ladder**: every quant is calibrated with an importance matrix. > [!NOTE] > These GGUFs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.
译文排队中 · 当前显示来源原文
**Qwen3.5 9B**, self-quantized to GGUF by Atomic Chat. Built straight from Qwen's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline. > [!NOTE] > These GGUFs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model. > [!IMPORTANT] > Always pass `--jinja` so the **Qwen3.5 9B chat template** is applied. Without it the model can emit malformed turns.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
**Qwen3.6 27B**, self-quantized to GGUF by Atomic Chat. Built straight from Qwen's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline. > [!NOTE] > These GGUFs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model. > [!IMPORTANT] > Always pass `--jinja` so the **Qwen3.6 27B chat template** is applied. Without it the model can emit malformed turns.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
**Qwen3.6 35B A3B**, self-quantized to GGUF by Atomic Chat. Built straight from Qwen's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline. > [!NOTE] > These GGUFs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model. > [!IMPORTANT] > Always pass `--jinja` so the **Qwen3.6 35B A3B chat template** is applied. Without it the model can emit malformed turns.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Built from Qwen's original weights with our own importance matrix. The calibration corpora behind our builds are public. Learn how to run Qwen3.8 27B locally - read our guide . You can now run Qwen3.8 in Atomic Chat with toggles for thinking. See our quantization analysis below for measurements and instructions. Every quantization of this model we could find, ours and everyone else's, measured against the original weights on the same held-out text. The dashed line is the best file available at each size from anyone but us.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
Built from Qwen's original weights with our own importance matrix. The calibration corpora behind our builds are public. Built by the team behind Atomic Chat , the app that runs open-weight models locally and offline. Qwen3.8-Flash-Next is the first open-weight release of the architecture behind Qwen4. These GGUFs are self-quantized from Qwen's original weights with our own importance matrix, published alongside the quants. They need a llama.cpp build with Qwen3.8-Flash-Next support; Atomic Chat runs it as support ships. Need it without refusals? Qwen3.8-Flash-Next-Uncensored-GGUF has baked builds and a LoRA adapter for the quants here. Qwen3.8-Flash-Next has 177B parameters. Our 85 GB quant runs on an M5 Max with 64 GB of memory, with vision, at 36 tok/s. That is not a typo: the file is larger than the machine's entire RAM.
译文排队中 · 当前显示来源原文
可以调整厂商、分类或输入输出条件；新模型正持续收录。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。
