GLM-5.3-Flash-NVFP4
local-inference-lab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 ↗DISCOVER & COMPARE
探索 AI 模型 85003
GLM-5.3-Flash-NVFP4-MXFP8-CSF-QAD
local-inference-lab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 ↗GLM-5.3-Flash-NVFP4-Spark
local-inference-labWe introduce GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series. With 320B total parameters and just 18B active parameters, it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks. GLM-5.3-Flash starts from a newly trained base model, with its architecture and training recipe redesigned around capability and efficiency. For the first time in the GLM series, we introduce a hybrid architecture combining sparse and linear attention, sharply reducing long-context serving costs while preserving precise long-context capabilities. The model also adopts Manifold-Constrained Hyper-Connections (mHC) to further improve scaling efficiency. Together with our latest 30T-token multimodal pre-training corpus, these changes enable GLM-5.3-Flash to deliver more intelligence with less compute.
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 ↗GLM-5.3-NVFP4
local-inference-lab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 ↗GLM-5.3-NVFP4-CSF
local-inference-lab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 ↗Qwen3.8-Flash-Next-NVFP4
local-inference-lablocal-inference-lab/Qwen3.8-Flash-Next-NVFP4 is a mixed-precision model distilled from Qwen/Qwen3.8-Flash-Next using quantization-aware distillation (QAD). The student is trained against the original BF16 teacher with quantized weights in its forward pass, learning to compensate for quantization error rather than relying on post-training quantization alone. The architecture is unchanged: 48 decoder layers, 512 routed experts per layer with 10 active per token, hybrid Gated DeltaNet/Qwen Sparse Attention (QSA), and n-gram embedding tables. Compression comes from lower-precision weights, not fewer layers or experts. The checkpoint occupies approximately 98 GiB on disk and is particularly suited to run on a single RTX 6000 (with PLE offload), or a DGX Spark (with or without PLE offload). NVFP4 stores 4-bit E2M1 values with FP8 block scales per 16 elements and an FP32 global scale. MXFP8 stores 8-bit E4M3 values with power-of-two block scales per 32 elements. Residual-mixing and PLE normalization weights are trained in FP32 and exported in BF16. Shared-expert scalar gates remain frozen in BF16.
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 ↗Qwen3.8-Flash-Next-NVFP4-MXFP8-CSF-QAD
local-inference-lab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 ↗Ninja-v1-NSFW-GGUF
Local-Novel-LLM-project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 ↗Vecteus-v1-gguf
Local-Novel-LLM-project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 ↗WabiSabi-V1.5-beta-GGUF
Local-Novel-LLM-project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 ↗piper-voices-GGUF
LocalAI-Community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 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗dinov3-vitl16-pretrain-lvd1689m-GGUF
LocalAI-io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 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗GEM-X-GGUF
LocalAI-io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 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Kimodo-G1-RP-v1-GGML
LocalAI-io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 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Kimodo-G1-SEED-v1-GGML
LocalAI-io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 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Kimodo-SOMA-RP-v1.1-GGML
LocalAI-ioNative F32 GGML/GGUF conversion of nvidia/Kimodo-SOMA-RP-v1.1. The model predicts the compact SOMA 30-joint control skeleton. Its reusable Llama-derived text encoder is distributed separately as `Llama-3-Kimodo-GGML`. The model is installed at `models/kimodo-soma-rp-v1.1-f32.gguf` by `scripts/download_gguf_weights.sh --output "$PWD" --model soma-rp-v1.1`. Converted from upstream revision `6c9233af1180b8151e3c4703477104af5dce9dd5`. `MANIFEST.json` records the source revision and SHA-256 of the GGUF. The model remains subject to the NVIDIA Open Model License. This conversion grants no additional rights.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Kimodo-SOMA-SEED-v1.1-GGML
LocalAI-io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 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Llama-3-Kimodo-GGML
LocalAI-ioNative GGML/GGUF text encoder used by Kimodo. This is the reusable LLM2Vec encoder only; download a matching Kimodo diffusion model separately, for example `Kimodo-SMPLX-RP-v1-GGML`. From a kimodo.cpp checkout with the Hugging Face CLI installed, install both with: The downloader installs the recommended Q8_0 variant by default. Select a different one with `--text-quantization bf16|q8_0|q6_k|q5_k|q4_k|q4_k_m`. Every variant is one monolithic weight GGUF and uses the same `tokenizer.gguf`. Kimodo reads individual tensor ranges from the monolith, so streaming one layer at a time does not require separate per-layer files.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗This model was converted to GGUF format from `mudler/LocalAI-functioncall-qwen2.5-7b-v0.5` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LocalVQE
LocalAI-io**Local Voice Quality Enhancement** — compact neural models for acoustic echo cancellation (AEC), noise suppression (NS), and dereverberation of 16 kHz speech, running on commodity CPUs in real time. Causal and streaming (256-sample hop, 16 ms latency). This page hosts the published weights. Inference runs the GGML C++ engine on the GGUF files directly (build instructions on GitHub). **Authors:** Richard Palethorpe (richiejp) and Claude (Anthropic). LocalVQE is a streaming, CPU-tuned derivative of **DeepVQE** (Indenbom et al., Interspeech 2023).
译文排队中 · 当前显示来源原文
输入 音频→ 输出 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗MotionBricks-G1-GGML
LocalAI-io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 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗privacy-filter-GGUF
LocalAI-io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 ↗privacy-filter-multilingual-GGUF
LocalAI-ioGGUF conversion of `OpenMed/privacy-filter-multilingual`, a multilingual PII **token-classification** model (a fine-tune of `openai/privacy-filter`). It labels every token with a BIOES tag over **54 PII categories (217 classes)** across **16 languages**, so it can be served locally with **no Python** as the encoder/NER tier of a PII redactor. For the full model description, label space, evaluation, limitations, and citations, see the **source model card** — this card only covers the GGUF packaging and how to run it. This GGUF uses a **custom architecture, `openai-privacy-filter`**, that is not (yet) part of upstream llama.cpp. It runs on:
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 ↗privacy-filter-nemotron-GGUF
LocalAI-ioGGUF conversion of `OpenMed/privacy-filter-nemotron`, a **fine-grained** PII **token-classification** model — a fine-tune of `openai/privacy-filter` on the `nvidia/Nemotron-PII` dataset. It labels every token with a BIOES tag over **55 PII categories (221 classes)** in a single forward pass, then decodes coherent spans with a constrained Viterbi procedure — so it can be served locally with **no Python** as the encoder/NER tier of a PII redactor. Where the base `openai/privacy-filter` covers 8 coarse categories, this fine-tune trades multilingual breadth for **category depth**: 55 fine-grained English categories (first/last name, government IDs, financial, healthcare, vehicle, digital, …). For the full model description, label space, evaluation, limitations, and citations, see the **source model card** — this card only covers the GGUF packaging and how to run it.
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 ↗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。