dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf
dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf is a 7 billion parameter chat model from pawelhoscilo, released March 1, 2026. dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf is an open-weights chat model with roughly 7 billion parameters.
by pawelhoscilo · 7B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your pawelhoscilo API key. osFoundry discovers dolphin-2.8-mistral-7b-v02.Q5_K_M_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
dolphin-2.8-mistral-7b-v02.Q5_K_M_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 dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf
dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf runs on a single 16GB consumer GPU (~5 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~17 GB).
dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf
Is dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf free to use?
dolphin-2.8-mistral-7b-v02.Q5_K_M_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 dolphin-2.8-mistral-7b-v02.Q5_K_M_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 dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf need?
Approximately 5 GB at Q4 quantisation, or 17 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf locally?
Yes. dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf best at?
dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf in osFoundry?
Paste your pawelhoscilo API key in the key dialog (or deploy the open weights for self-hostable models), assign dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by pawelhoscilo on March 1, 2026. Source: https://huggingface.co/pawelhoscilo/dolphin-2.8-mistral-7b-v02.Q5_K_M_gguf