HostYourAI
Product
EU RouterOpenAI-compatible APIAnthropic-compatible APIModel GardenDedicated InstancesPlaygroundFine-tuning (Loes)Connect your GPU pool
Solutions
Use cases
LLM InferenceRAG pipelinesChatbotsAI agentsFine-tuning
Industries
GovernmentHealthcareFinanceLegal
Models
Llama 3.3 70BMistralDeepSeek R1Qwen 2.5 72BGemma 2 27BCodestral 22BAll models →
Compare
Azure OpenAIAWS BedrockClaude APIChatGPTOpenAI
Resources
DocumentationGuide: migrate to the EU RouterGuide: deploy your own LLM (vLLM)Guide: build RAG on EU GPUsModel catalog
Pricing
NL EN DE
Login Book Demo Get Started
Model garden On request

Llama Poro 2 8B SFT

This model runs as a dedicated deployment on large GPUs and isn't in the shared playground by default. Get in touch and we'll set it up for you.

Note for most users: This is an intermediate checkpoint from our post-training pipeline. Most users should use Poro 2 8B Instruct instead, which includes an additional round of Direct Preference Optimization (DPO) for improved response quality and alignment. This SFT-only model i...

Request access ← All models
LumiOpen/Llama-Poro-2-8B-SFT On request
text->text · LumiOpen · EU-hosted
8B
Parameters
8K
Context window
24GB
Minimum VRAM
POST /api/v1/chat/completions On request

Specifications

Parameters 8B
Context window 8,192 tokens
Minimum VRAM 24 GB
Architecture LlamaForCausalLM (vLLM)
License llama3.3
Modality text->text
Released June 2025
Publisher LumiOpen ↗

Pricing

€0.05
Input (per 1M tokens)
€0.12
Output (per 1M tokens)

Shared EU router, pay-per-token, scale-to-zero. Dedicated GPU deployments are billed hourly, see pricing.

Not available on the shared router. Pricing on request as a dedicated GPU deployment.

Call it now

Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.

curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "LumiOpen/Llama-Poro-2-8B-SFT",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run Llama Poro 2 8B SFT in the EU?

Yes. HostYourAI runs Llama Poro 2 8B SFT on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.

Is hosting Llama Poro 2 8B SFT GDPR-compliant?

Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.

How much does Llama Poro 2 8B SFT cost?

Via the shared EU router you pay €0.05 per million input tokens and €0.12 per million output tokens, with no fixed costs. For high volume or isolation you can also run Llama Poro 2 8B SFT as a dedicated hourly GPU instance.

Is the API OpenAI-compatible?

Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.

More models from LumiOpen

Llama Poro 2 70B SFT

Note for most users: This is an intermediate checkpoint from our post-training pipeline. Most users should use Poro 2 70B Instruct instead, which includes an additional round of Direct Preference Optimization (DPO) for improved response quality and alignment. This SFT-only model is primarily intended for researchers interested in studying the effects of different post-training techniques.

71B 8K context View model →
Llama Poro 2 70B base

Poro 2 70B Base is a 70B parameter decoder-only transformer created through continued pretraining of Llama 3.1 70B to add Finnish language capabilities. It was trained on 165B tokens using a carefully balanced mix of Finnish, English, code, and math data. Poro 2 is a fully open source model and is made available under the Llama 3.1 Community License.

71B 8K context View model →
Llama Poro 2 8B base

Poro 2 8B Base is an 8B parameter decoder-only transformer created through continued pretraining of Llama 3.1 8B to add Finnish language capabilities. It was trained on 165B tokens using a carefully balanced mix of Finnish, English, code, and math data. Poro 2 is a fully open source model and is made available under the Llama 3.1 Community License.

8B 8K context View model →
Llama Poro 2 70B Instruct

Poro 2 70B Instruct is an instruction-following chatbot model created through supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) of the Poro 2 70B Base model. This model is designed for conversational AI applications and instruction following in both Finnish and English. It was trained on a carefully curated mix of English and Finnish instruction data, followed by preference tuning to improve response quality.

71B 8K context View model →
Llama Poro 2 8B Instruct

Poro 2 8B Instruct is an instruction-following chatbot model created through supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) of the Poro 2 8B Base model. This model is designed for conversational AI applications and instruction following in both Finnish and English. It was trained on a carefully curated mix of English and Finnish instruction data, followed by preference tuning to improve response quality.

8B 8K context View model →
Poro 34B chat

Poro 34b chat is a chat-tuned version of Poro 34B trained to follow instructions in both Finnish and English. Quantized versions are available on Poro 34B-chat-GGUF.

34B View model →

Request access

Llama Poro 2 8B SFT isn't available by default yet. Leave your details and we'll arrange a dedicated deployment.

Request access