Qwen 3.8 27B available on Cerebras at 1500 tokens/s
Qwen 3.8 27B available on Cerebras at 1500 tokens/s
Qwen 3.8 27B 现已上线 Cerebras，速度达 1500 tokens/s
Models on Cerebras public endpoints are available on the free trial and pay-as-you-go tiers, subject to rate limits and pricing. For additional model families, reserved capacity, higher throughput, and production SLAs, see Dedicated Endpoints. New here? Follow the Quickstart to make your first API call. To pick a model by use case, see the model selection guide. Select any model name below for full specs, capabilities, and per-tier limits.
Cerebras 公共端点上的模型适用于免费试用和按需付费层级，并受速率限制和定价约束。如需更多模型系列、预留容量、更高吞吐量以及生产级 SLA，请参阅“专用端点”（Dedicated Endpoints）。新用户请参考“快速入门”（Quickstart）进行首次 API 调用。若需根据用例选择模型，请查看模型选择指南。点击下方任意模型名称即可查看完整规格、功能及各层级的限制。
Available Models
可用模型
| Model Name | Model ID | Parameters | Context (free / paid) | Speed (tokens/s) |
|---|---|---|---|---|
| OpenAI GPT OSS | gpt-oss-120b | 120 billion | 65k / 131k | ~3000 |
| Qwen 3.8 27B | qwen-3.8-27b | 27 billion | 64k / 128k | ~1500 |
Looking for more models? Many additional model families are available through Dedicated Endpoints.
正在寻找更多模型？通过“专用端点”可以使用更多模型系列。
Model Compression
模型压缩
This section provides transparency about the compression state of each model available on our platform. We host a variety of open-source models from the community. We do not currently host pruned models on our public endpoints. All models served through our public endpoints are the original, unpruned versions. While we conduct research on pruning techniques like REAP (Router-weighted Expert Activation Pruning), these pruned models are shared with the research community on Hugging Face but are not available through our shared API. You can read more about REAP in our research blog. All of our public models are unpruned.
本节旨在透明地说明我们平台上每个模型的压缩状态。我们托管了来自社区的各种开源模型。目前，我们的公共端点不托管经过剪枝（pruned）的模型。所有通过公共端点提供的模型均为原始的、未剪枝版本。虽然我们正在研究诸如 REAP（路由加权专家激活剪枝）等剪枝技术，但这些剪枝模型仅在 Hugging Face 上与研究社区共享，并不通过我们的共享 API 提供。您可以在我们的研究博客中阅读有关 REAP 的更多信息。我们所有的公共模型均为未剪枝版本。
Cerebras uses selective weight-only quantization only during storage to preserve maximal quality. This means that the weights are stored in partial 16-bit / 8-bit / 4-bit, in-line with industry standards. For quality, sensitive layers are stored at full precision with dequantization on the fly, so operations are done in high precision. The activations, attention, and kv cache remain in full precision and unquantized.
Cerebras 仅在存储期间使用选择性的“仅权重”量化（weight-only quantization），以保持最高质量。这意味着权重按照行业标准以 16 位 / 8 位 / 4 位存储。为了保证质量，敏感层以全精度存储，并在运行时进行反量化，从而确保运算在高精度下完成。激活值、注意力机制和 KV 缓存保持全精度且未量化。
Frequently Asked Questions
常见问题解答
Will you change a model’s architecture without notice? No. We are committed to serving the original models for all existing endpoints, without modification. We do not alter model architectures via pruning on our hosted portfolio. If we explore additional compression techniques (like pruning) in the future, these would be offered as separate endpoints with pruning-specific names, ensuring complete transparency and allowing you to choose which version best fits your needs.
你们会不经通知更改模型架构吗？ 不会。我们致力于为所有现有端点提供原始模型，不做任何修改。我们不会通过剪枝来改变托管组合中的模型架构。如果我们未来探索其他压缩技术（如剪枝），这些模型将作为带有剪枝特定名称的独立端点提供，以确保完全透明，并允许您选择最适合您需求的版本。
Where can I find your REAP pruned models? Our REAP pruned models are available on Hugging Face for research and experimentation purposes: Cerebras REAP Collection. These models demonstrate our pruning research but are not served through our production API.
在哪里可以找到你们的 REAP 剪枝模型？ 我们的 REAP 剪枝模型可在 Hugging Face 上获取，供研究和实验使用：Cerebras REAP Collection。这些模型展示了我们的剪枝研究成果，但不会通过我们的生产 API 提供。
What are compression, quantization, and pruning? Compression is an umbrella term for techniques that reduce model size or computational requirements. Common compression techniques include:
- Quantization: Reducing the precision of numbers used to represent model weights (e.g., converting from FP16 to FP8). This reduces memory usage without changing the model’s architecture.
- Pruning: Permanently removing parts of a model, like layers or experts, to reduce model size. This changes the model’s architecture and creates a different model.
什么是压缩、量化和剪枝？ 压缩是一个总称，指代减少模型大小或计算需求的技术。常见的压缩技术包括：
- 量化（Quantization）： 降低用于表示模型权重的数字精度（例如，从 FP16 转换为 FP8）。这可以在不改变模型架构的情况下减少内存使用。
- 剪枝（Pruning）： 永久移除模型的一部分（如层或专家），以减小模型大小。这会改变模型的架构并创建一个不同的模型。