GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF
GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF (andyjack, 2026) is a 268 billion parameter chat model. GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF is an open-weights chat model with roughly 268 billion parameters.
by andyjack · 268B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your andyjack API key. osFoundry discovers GLM-4.7-REAP-268B-A32B-MXFP4_MOE_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
GLM-4.7-REAP-268B-A32B-MXFP4_MOE_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 GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF
GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF runs on a multi-GPU setup or H200 141GB at Q4 (~161 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~644 GB).
GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF
Is GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF free to use?
GLM-4.7-REAP-268B-A32B-MXFP4_MOE_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 GLM-4.7-REAP-268B-A32B-MXFP4_MOE_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 GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF need?
Approximately 161 GB at Q4 quantisation, or 644 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF locally?
Yes. GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF best at?
GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF in osFoundry?
Paste your andyjack API key in the key dialog (or deploy the open weights for self-hostable models), assign GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by andyjack on March 11, 2026. Source: https://huggingface.co/andyjack/GLM-4.7-REAP-268B-A32B-MXFP4_MOE_GGUF