Beam-1.0-501B-A23B-GGUF
AtomicChat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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 86
d1-3B-GGUF
AtomicChat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。
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗d1-omni-600M-GGUF
AtomicChat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
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗The DwarfStar (ds4) Q2 build of DeepSeek-V4.1-Flash-1017 with DeepSeek's refusal direction projected out of the weights. Built by the team behind Atomic Chat , the app that runs open-weight models locally and offline. - This is antirez/deepseek-v4.1-flash-gguf's `DeepSeek-V4.1-Flash-1017-IQ2_XXS-Q2_K-imatrix.gguf` (revision `9dcee51692e6`) with **only the 122 tensors that write into the residual stream replaced**: attention output (`attn_output_b`), shared-expert down projection, the down projection of all 384 routed experts of every block, and Engram's value projection. Every other byte, the header included, is the original's, so it runs wherever that file runs, in the same memory. - The replaced tensors carry the edit of AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF (one direction, strength 2.0), baked into DeepSeek's weights at full precision and quantized to the original file's types (Q8_0, Q2_K with an importance matrix, F16). After the bake, 99.98% of the edit is in every writer.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DeepSeek-V4.1-Flash-1017-Uncensored-GGUF
AtomicChatDeepSeek's refusal direction projected out of the released weights, baked into GGUF builds and measured against the original. **`2.67bpw-IQ1_M` costs knowledge.** It answers without refusals like the other build, but at 1 bit the edit takes MMLU from 85.6% to 81.8% (500 questions, p = 0.003; our gate allows 1.5 points), and it did not pass that gate. With thinking on it also goes round more often (3/30 looping traces at low effort and 5/30 at high on JailbreakBench). It is here for machines with about 140 GB for the weights; if `3.58bpw-Q2_K` fits, take that one. Neutral held-out text, 24 chunks of 4096 tokens, against Unsloth's UD-Q8_K_XL (the converter's BF16 + native MXFP4 output of the released checkpoint) as the reference.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DeepSeek-V4-Flash-0731-GGUF
AtomicChat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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗embeddinggemma-2-GGUF
AtomicChat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。
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Flint-GGUF
AtomicChatBuilt from RecursiveSI'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. Flint is RecursiveSI's 39.8B mixture-of-experts coding model. About 2.5B parameters are active per token. See our measurements below, including how these files compare to other builds of Flint. Generate about 1.5 times faster with the DFlash2 draft model: the command and our speed measurements are in Faster with DFlash2 . 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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗FLUX-3-Image-Klein-GGUF
AtomicChatBlack Forest Labs' FLUX 3 Image Klein as GGUF for stable-diffusion.cpp, built from the published BF16 weights with our own importance matrix and measured on one stand against every other Klein GGUF we could find. The renders and measurements are public. Built by the team behind Atomic Chat , the app that runs open-weight models locally and offline. Everything to run Klein in stable-diffusion.cpp is here: the image model, the Qwen3-VL-4B text encoder ( text_encoders/ ) and the autoencoder ( vae/ ). The image model files also load in ComfyUI through ComfyUI-GGUF; see In ComfyUI . The prompt upsampler Klein expects is in FLUX-3-Image-Klein-pup-GGUF . AD-Q5_K stays 14% closer to the BF16 picture than unsloth's UD-Q5_K_XL at a smaller size, and AD-Q4_K 21% closer than their Q4_K_M . Where their file is better, the table below says so. The text encoder moves the picture as much as the image model does. Our AD-Q4_K encoder is 21% closer than the Q4_K_M most people use, at the same size. Looking for uncensored? The open Klein pipeline has no content filter. Our text encoder and prompt upsampler without refusals are in FLUX-3-Image-Klein-TE-Uncensored-GGUF and FLUX-3-Image-Klein-pup-Uncensored-GGUF ; what they change on the pictures is in Content filtering . FLUX 3 Image Klein is Black Forest Labs' 5.6B text-to-image and editing model: one model for generation, single-reference edits and up to ten reference images, distilled to **16 steps at CFG 1**. This repo has the image model as GGUF for stable-diffusion.cpp, with the text encoder and the autoencoder next to it.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 图像
价格待核验多模态与渠道费用须分别核对
查看详情 ↗FLUX-3-Image-Klein-pup-GGUF
AtomicChat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。
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗FLUX-3-Image-Klein-pup-Uncensored-GGUF
AtomicChatBFL's prompt upsampler for FLUX 3 Image Klein (a 9B Qwen3.5 fine-tune) with its refusal direction projected out, as GGUF for llama.cpp, plus the same edit as a LoRA for the stock files. Klein's text encoder without refusals is in FLUX-3-Image-Klein-TE-Uncensored-GGUF . The measurements are public. Built by the team behind Atomic Chat , the app that runs open-weight models locally and offline. As a chat model, refusals fall from 63% to 0% on held-out English prompts. MMLU goes from 74.15% to 73.95%. As Klein's upsampler, under BFL's t2i system prompt, the stock model refuses none of our requests but softens 2 of 35 sensitive ones in its captions; this one keeps them. The image model draws neither of the two in any build , so on Klein's pictures we measured no uncensoring effect; the open pipeline already draws the sensitive categories ( the per-category table ). Against the other uncensored upsamplers on our stand, prithiv's measures the same as this one, and Sakura's still refuses 22% in English. The same rungs and layouts as our stock upsampler GGUFs, with the edit baked in. KLD and top-1 are against the original BF16 on a 30-language neutral text set (87 chunks of 4096 tokens), so they include the edit itself. Refusals are on held-out prompts (81 English harmful requests; 250 XSTest safe prompts), plain chat, thinking off.
译文排队中 · 当前显示来源原文
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗FLUX-3-Image-Klein-TE-Uncensored-GGUF
AtomicChatFLUX 3 Image Klein's text encoder, Qwen3-VL-4B-Instruct, with its refusal direction projected out: a drop-in --llm for stable-diffusion.cpp next to our Klein GGUFs . Klein's prompt upsampler without refusals is in FLUX-3-Image-Klein-pup-Uncensored-GGUF . Below, exactly which part is uncensored and what that does to the pictures. The measurements are public. Built by the team behind Atomic Chat , the app that runs open-weight models locally and offline. As a chat model, the encoder's refusals fall from 79% to 0% on held-out English prompts. MMLU goes from 71.1% to 71.2%. On images it changes nothing we could measure. The open Klein pipeline has no filter and already draws the sensitive categories we tested. With this encoder, alone or together with the uncensored upsampler, no category moved by more than one picture in ten. See where exactly this is uncensored . Another uncensored Klein encoder, webmp3's Sakura, has a smaller edit: it moves the model and the pictures less than this one, at the same 0% refusals. See the comparison . FLUX 3 Image Klein makes a picture with four parts. Two of them are changed in our Uncensored releases, one in each repo.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 图像
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-12B-it-GGUF
AtomicChat**Gemma 4 12b**, self-quantized to GGUF by Atomic Chat. Built straight from Google's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline. - **11.95B parameters**: the weights this repo quantizes. - **Context length**: 256K tokens, as published by Google. - **48 layers**: Dense decoder, hybrid sliding-window (1024) and global attention. - **Modalities**: Text, Image, Audio. - **Full imatrix ladder**: every quant is calibrated with an importance matrix, published here alongside the quants. - **Reasoning**: All models in the family are designed as highly capable reasoners, with configurable thinking modes. - **Diverse & Efficient Architectures**: Offers Dense and Mixture-of-Experts (MoE) variants of different sizes for scalable deployment. > [!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
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-12B-it-MLX-4bit
AtomicChat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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-26B-A4B-it-assistant-GGUF
AtomicChat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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-26B-A4B-it-GGUF
AtomicChat**Gemma 4 26B A4B**, self-quantized to GGUF by Atomic Chat. Built straight from Google'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 **Gemma 4 26B A4B 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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-26B-A4B-it-MLX-4bit
AtomicChat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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-31B-it-assistant-GGUF
AtomicChat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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-31B-it-GGUF
AtomicChat**Gemma 4 31B**, self-quantized to GGUF by Atomic Chat. Built straight from Google'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 **Gemma 4 31B 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
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-E2B-it-assistant-GGUF
AtomicChat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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-E2B-it-GGUF
AtomicChat**Gemma 4 E2B**, self-quantized to GGUF by Atomic Chat. Built straight from Google'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 **Gemma 4 E2B 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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-E4B-it-assistant-GGUF
AtomicChat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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-E4B-it-GGUF
AtomicChat**Gemma 4 E4B**, self-quantized to GGUF by Atomic Chat. Built straight from Google's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline. - **4.5B effective (8B with embeddings) parameters**: the weights this repo quantizes. - **Context length**: 128K tokens, as published by Google. - **42 layers**: Dense decoder, hybrid sliding-window (512) and global attention. - **Modalities**: Text, Image, Audio. - **Full imatrix ladder**: every quant is calibrated with an importance matrix, published here alongside the quants. - **Reasoning**: All models in the family are designed as highly capable reasoners, with configurable thinking modes. - **Diverse & Efficient Architectures**: Offers Dense and Mixture-of-Experts (MoE) variants of different sizes for scalable deployment. > [!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
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Inkling-GGUF
AtomicChat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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
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。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
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。
开放权重，就代表可以免费商用吗？+
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。
排行榜第一，就是最适合我的模型吗？+
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。