AWQ quantization: done by stelterlab in INT4 GEMM with AutoAWQ by casper-hansen (https://github.com/casper-hansen/AutoAWQ/) Mistral Small 3 ( 2501 ) sets a new benchmark in the "small" Large Language Models category below 70B, boasting 24B parameters and achieving state-of-the-art capabilities comparable to larger models! This model is an instruction-fine-tuned version of the base model: Mistral-Small-24B-Base-2501. Mistral Small can be deployed locally and is exceptionally "knowledge-dense", fitting in a single RTX 4090 or a 32GB RAM MacBook once quantized. Perfect for: - Fast response conversational agents. - Low latency function calling. - Subject matter experts via fine-tuning. - Local inference for hobbyists and organizations handling sensitive data.

译文排队中 · 当前显示来源原文

文本生成

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 ↗

加入对比来源 / 文档 ↗

Mistral-Small-3.2-24B-Instruct-2506-FP8

stelterlab

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。

视觉问答

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 ↗

加入对比来源 / 文档 ↗

NVIDIA-Nemotron-3-Nano-30B-A3B-AWQ

stelterlab

AWQ quantization: done by stelterlab in INT4 GEMM with llm-compressor (https://github.com/vllm-project/llm-compressor - v0.9.0.1) from the vllm-project. See recipe.yaml. Did some basic tests against vLLM v0.15.0 (official docker image). Nemotron-Nano-3-30B-A3B-FP8 is a quantized version of Nemotron-Nano-3-30B-A3B and is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be configured through a flag in the chat template. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in accuracy for harder prompts that require reasoning. Conversely, allowing the model to generate reasoning traces first generally results in higher-quality final solutions to queries and tasks. The model employs a hybrid Mixture-of-Experts (MoE) architecture, consisting of 23 Mamba-2 and MoE layers, along with 6 Attention layers. Each MoE layer includes 128 experts plus 1 shared expert, with 6 experts activated per token. The model has 3.5B active parameters and 30B parameters in total.

译文排队中 · 当前显示来源原文

文本生成

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 ↗

加入对比来源 / 文档 ↗

phi-4-AWQ

stelterlab

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。

文本生成

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 ↗

加入对比来源 / 文档 ↗

Qwen3-30B-A3B-Instruct-2507-AWQ

stelterlab

AWQ quantization: done by stelterlab in INT4 GEMM with llm-compressor (https://github.com/vllm-project/llm-compressor) from the vllm-project. Still trying to get familiar with llm-compressor. Tested against vLLM v0.9.2. We introduce the updated version of the **Qwen3-30B-A3B non-thinking mode**, named **Qwen3-30B-A3B-Instruct-2507**, featuring the following key enhancements: - **Significant improvements** in general capabilities, including **instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage**. - **Substantial gains** in long-tail knowledge coverage across **multiple languages**. - **Markedly better alignment** with user preferences in **subjective and open-ended tasks**, enabling more helpful responses and higher-quality text generation. - **Enhanced capabilities** in **256K long-context understanding**.

译文排队中 · 当前显示来源原文

文本生成

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 ↗

加入对比来源 / 文档 ↗

Qwen3-Coder-30B-A3B-Instruct-AWQ

stelterlab

**Updated** AWQ quantization: done by stelterlab in INT4 GEMM with llm-compressor (https://github.com/vllm-project/llm-compressor) from the vllm-project. Still trying to get familiar with llm-compressor. **Qwen3-Coder** is available in multiple sizes. Today, we're excited to introduce **Qwen3-Coder-30B-A3B-Instruct**. This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements: - **Significant Performance** among open models on **Agentic Coding**, **Agentic Browser-Use**, and other foundational coding tasks. - **Long-context Capabilities** with native support for **256K** tokens, extendable up to **1M** tokens using Yarn, optimized for repository-scale understanding. - **Agentic Coding** supporting for most platform such as **Qwen Code**, **CLINE**, featuring a specially designed function call format.

译文排队中 · 当前显示来源原文

文本生成

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 ↗

加入对比来源 / 文档 ↗

COST EXPLORER

好模型，也要算好成本。

费用分析

调整月度 Token 用量，直观比较不同模型的预估 API 开支。

每月输入 Token 10 M每月输出 Token 2 M1 M = 100 万 Token · 美元计价
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

选型与常见问题

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。

找到适合你的 AI 模型。

探索 AI 模型 7

DeepSeek-R1-Distill-Qwen-14B-AWQ

Mistral-Small-24B-Instruct-2501-AWQ

Mistral-Small-3.2-24B-Instruct-2506-FP8

NVIDIA-Nemotron-3-Nano-30B-A3B-AWQ

phi-4-AWQ

Qwen3-30B-A3B-Instruct-2507-AWQ

Qwen3-Coder-30B-A3B-Instruct-AWQ

暂未找到匹配模型

好模型，也要算好成本。

读懂模型，再做选择

资讯看趋势，工具提效率，模型筑可能。