(../mintlify-assets/_next/static/media/83afe278b6a6bb3c.p.3a6ba036.woff2)  (../mintlify-assets/_next/static/media/PaperMono_Variable.p.aa32f7a0.woff2)  (../mintlify-assets/_next/static/media/f67ad414ed34149c.p.84166d94.woff2)  (../../mintcdn.com/cerebras-inference/b3jx4ZXgBWCXv7Rn/logo/2.png@fit=max&auto=format&n=b3jx4ZXgBWCXv7Rn&q=85&s=98684d23487c722617419a5dbeb0c678)  (../../mintcdn.com/cerebras-inference/b3jx4ZXgBWCXv7Rn/logo/1.png@fit=max&auto=format&n=b3jx4ZXgBWCXv7Rn&q=85&s=7710d16c35881e9aa3b9c98143774cbb)  (../mintlify-assets/_next/static/chunks/462bacc63bed9960.css@dpl=dpl_6R59ozTcM1rr5cnWyvW44ngfvPL3.css)  (../mintlify-assets/_next/static/chunks/bf5dec8f24f39796.css@dpl=dpl_6R59ozTcM1rr5cnWyvW44ngfvPL3.css)  (../mintlify-assets/_next/static/chunks/6d55b684068fd47e.js@dpl=dpl_6R59ozTcM1rr5cnWyvW44ngfvPL3)  (https://fonts.googleapis.com)  (https://fonts.gstatic.com)  (https://fonts.googleapis.com)  (https://fonts.gstatic.com)  (https://d4tuoctqmanu0.cloudfront.net/katex.min.css)  Model Catalog - Cerebras Inference       (overview.html)  (https://inference-docs.cerebras.ai/sitemap.xml)  (https://inference-docs.cerebras.ai/models/overview.md)                (../mintlify-assets/_mintlify/favicons/cerebras-inference/FcAuEx9Fi3BOAJGk/_generated/favicon/android-chrome-192x192.png)  (https://inference-docs.cerebras.ai/mintlify-assets/_mintlify/favicons/cerebras-inference/FcAuEx9Fi3BOAJGk/_generated/favicon/apple-touch-icon.png)  (../mintlify-assets/_mintlify/favicons/cerebras-inference/FcAuEx9Fi3BOAJGk/_generated/favicon/favicon-16x16.png)  (../mintlify-assets/_mintlify/favicons/cerebras-inference/FcAuEx9Fi3BOAJGk/_generated/favicon/favicon-32x32.png)  (../mintlify-assets/_mintlify/favicons/cerebras-inference/FcAuEx9Fi3BOAJGk/_generated/favicon/favicon.ico)  (../mintlify-assets/_mintlify/favicons/cerebras-inference/FcAuEx9Fi3BOAJGk/_generated/favicon-dark/android-chrome-192x192.png)  (../mintlify-assets/_mintlify/favicons/cerebras-inference/FcAuEx9Fi3BOAJGk/_generated/favicon-dark/favicon-16x16.png)  (../mintlify-assets/_mintlify/favicons/cerebras-inference/FcAuEx9Fi3BOAJGk/_generated/favicon-dark/favicon-32x32.png)  (../mintlify-assets/_mintlify/favicons/cerebras-inference/FcAuEx9Fi3BOAJGk/_generated/favicon-dark/favicon.ico)    Documentation Index Fetch the complete documentation index at:(https://inference-docs.cerebras.ai/llms.txt) /llms.txt  Use this file to discover all available pages before exploring further.  (../../fonts.googleapis.com/css2@family=Manrope%253Aital,wght@0,400%3B0,500%3B0,600%3B0,700%3B0,800%3B1,400%3B1,500%3B1,600%3B1,700%3B1,800&display=swap.css)  (../../fonts.googleapis.com/css2@family=Manrope%253Aital,wght@0,400%3B0,500%3B0,600%3B0,700%3B0,800%3B1,400%3B1,500%3B1,600%3B1,700%3B1,800&display=swap.css)    (overview.html#content-area) Skip to main content   (https://inference-docs.cerebras.ai/) Cerebras Inferencehome page (light logo)  (dark logo)     (https://inference-docs.cerebras.ai/quickstart) Docs  (https://inference-docs.cerebras.ai/api-reference/authentication) API Reference  (https://inference-docs.cerebras.ai/integrations) Integrations  (https://inference-docs.cerebras.ai/cookbook) Cookbook    (https://discord.gg/a5TYzrJ444) Community   (https://www.cerebras.ai/blog) Blog   (https://cloud.cerebras.ai/?utm_source=3pi_docs&utm_campaign=navigation) Cloud Console   (https://cloud.cerebras.ai/?utm_source=3pi_docs&utm_campaign=navigation) Cloud Console         Search...             Navigation      Model Catalog    Model Catalog         Search...  ⌘K        (https://github.com/Cerebras/cerebras-cloud-sdk-python)  Python SDK   (https://github.com/Cerebras/cerebras-cloud-sdk-node)  Node.js SDK    Get Started   (https://inference-docs.cerebras.ai/quickstart) Quickstart     (https://www.cerebras.ai/pricing) Pricing         (https://inference-docs.cerebras.ai/support/rate-limits) Rate Limits       Models   Model Catalog      (https://inference-docs.cerebras.ai/models/qwen-3.8-27b) Qwen 3.8 27B     (https://inference-docs.cerebras.ai/models/openai-oss) OpenAI GPT OSS       (https://inference-docs.cerebras.ai/models/choose-a-model) Choose a Model       Capabilities   (https://inference-docs.cerebras.ai/capabilities/reasoning) Reasoning     (https://inference-docs.cerebras.ai/capabilities/streaming) Streaming Responses     (https://inference-docs.cerebras.ai/capabilities/structured-outputs) Structured Outputs     (https://inference-docs.cerebras.ai/capabilities/tool-use) Tool Calling     (https://inference-docs.cerebras.ai/capabilities/prompt-caching) Prompt Caching     (https://inference-docs.cerebras.ai/capabilities/image-inputs) Image Inputs Preview       (https://inference-docs.cerebras.ai/capabilities/payload-optimization) Payload Optimization       Dedicated Endpoints   (https://inference-docs.cerebras.ai/dedicated/overview) Overview     Features         Compatibility   (https://inference-docs.cerebras.ai/resources/openai) OpenAI Compatibility       Cloud Console   (https://inference-docs.cerebras.ai/console/overview) Overview     (https://inference-docs.cerebras.ai/console/projects) Projects     (https://inference-docs.cerebras.ai/console/api-keys) API Keys     (https://inference-docs.cerebras.ai/console/playground) Playground     (https://inference-docs.cerebras.ai/console/usage-monitoring) Usage & Monitoring     (https://inference-docs.cerebras.ai/console/account-billing) Account & Billing       Resources   (https://inference-docs.cerebras.ai/resources/designing-for-cerebras) Designing for Cerebras       Support   (https://status.cerebras.ai/) Service Status         (https://inference-docs.cerebras.ai/support/error) Error Codes     (https://inference-docs.cerebras.ai/support/change-log) Change Log     (https://inference-docs.cerebras.ai/support/deprecation) Deprecations     (https://www.cerebras.ai/policies) Policies         (https://inference-docs.cerebras.ai/support/preview-releases) Preview Releases                                         On this page   (overview.html#available-models) Available Models  (overview.html#model-compression) Model Compression (overview.html#frequently-asked-questions) Frequently Asked Questions           Copy page     Copy MCP Server       View as Markdown           (https://inference-docs.cerebras.ai/models/qwen-3.8-27b) Models    (overview.html) Model Catalog   Model Catalog   Browse all models available on Cerebras public endpoints.   Models on Cerebras public endpoints are available on the free trial and pay-as-you-go tiers, subject to (https://inference-docs.cerebras.ai/support/rate-limits) rate limits and (https://inference-docs.cerebras.ai/support/pricing) pricing . For additional model families, reserved capacity, higher throughput, and production SLAs, see (https://inference-docs.cerebras.ai/dedicated/overview) Dedicated Endpoints .    New here? Follow the (https://inference-docs.cerebras.ai/quickstart) Quickstart to make your first API call. To pick a model by use case, see the (https://inference-docs.cerebras.ai/models/choose-a-model) model selection guide . Select any model name below for full specs, capabilities, and per-tier limits.   (overview.html#available-models) ​      Available Models  Model Name Model ID Parameters Context (free / paid) Speed (tokens/s)   (https://inference-docs.cerebras.ai/models/openai-oss) OpenAI GPT OSS  gpt-oss-120b  120 billion 65k / 131k ~3000  (https://inference-docs.cerebras.ai/models/qwen-3.8-27b) Qwen 3.8 27B  qwen-3.8-27b  27 billion 64k / 128k ~1500           Looking for more models? Many additional model families are available through (https://inference-docs.cerebras.ai/dedicated/overview#supported-models) Dedicated Endpoints .   (overview.html#model-compression) ​      Model Compression  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 (https://www.cerebras.ai/blog/reap) research blog . All of our public models are unpruned.  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. (overview.html#frequently-asked-questions) ​      Frequently Asked Questions      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.       Where can I find your REAP pruned models?   Our REAP pruned models are available on Hugging Face for research and experimentation purposes: (https://huggingface.co/collections/cerebras/cerebras-reap) Cerebras REAP Collection . These models demonstrate our pruning research but are not served through our production API.       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.     Was this page helpful?    Yes     No       (https://inference-docs.cerebras.ai/support/rate-limits) Rate Limits   Previous    (https://inference-docs.cerebras.ai/models/qwen-3.8-27b) Qwen 3.8 27B   Next     (Ask a question...)  ⌘I                     Assistant               Responses are generated using AI and may contain mistakes.    (Ask a question...)