Replete-Coder-V2-Llama-3.1-8b-GGUF
Replete-Coder-V2-Llama-3.1-8b-GGUF is a 8 billion parameter chat model from QuantFactory, released August 23, 2024. Replete-Coder-V2-Llama-3.1-8b-GGUF is an open-weights chat model with roughly 8 billion parameters.
by QuantFactory · 8B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Replete-Coder-V2-Llama-3.1-8b-GGUF in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your QuantFactory API key. osFoundry discovers Replete-Coder-V2-Llama-3.1-8b-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
Replete-Coder-V2-Llama-3.1-8b-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 Replete-Coder-V2-Llama-3.1-8b-GGUF
Replete-Coder-V2-Llama-3.1-8b-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 (~20 GB).
Replete-Coder-V2-Llama-3.1-8b-GGUF vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Replete-Coder-V2-Llama-3.1-8b-GGUF
Is Replete-Coder-V2-Llama-3.1-8b-GGUF free to use?
Replete-Coder-V2-Llama-3.1-8b-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 Replete-Coder-V2-Llama-3.1-8b-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 Replete-Coder-V2-Llama-3.1-8b-GGUF need?
Approximately 5 GB at Q4 quantisation, or 20 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Replete-Coder-V2-Llama-3.1-8b-GGUF locally?
Yes. Replete-Coder-V2-Llama-3.1-8b-GGUF is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Replete-Coder-V2-Llama-3.1-8b-GGUF best at?
Replete-Coder-V2-Llama-3.1-8b-GGUF is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Replete-Coder-V2-Llama-3.1-8b-GGUF in osFoundry?
Paste your QuantFactory API key in the key dialog (or deploy the open weights for self-hostable models), assign Replete-Coder-V2-Llama-3.1-8b-GGUF to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by QuantFactory on August 23, 2024. Source: https://huggingface.co/QuantFactory/Replete-Coder-V2-Llama-3.1-8b-GGUF