Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF
Built by wimmmm, Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF is a 149 billion parameter chat model. Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF is an open-weights chat model with roughly 149 billion parameters.
by wimmmm · 149B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your wimmmm API key. osFoundry discovers Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
What hardware can run Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF
Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF runs on a multi-GPU setup or H200 141GB at Q4 (~90 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~358 GB).
Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF
Is Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF free to use?
Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF need?
Approximately 90 GB at Q4 quantisation, or 358 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF locally?
Yes. Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF best at?
Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF in osFoundry?
Paste your wimmmm API key in the key dialog (or deploy the open weights for self-hostable models), assign Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by wimmmm on March 20, 2026. Source: https://huggingface.co/wimmmm/Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF