The request names a specific fine-tuned model ID (a Llama 3 8B Instruct LoRA adapter), which none of the candidate sources list directly. The closest matches are hosts that run Llama 3 8B Instruct, where that base model can be called through an API 212, and Meta's own base model is named on Replicate's action record 12. The identifier itself could not be matched to a registry entry, so the exact checkpoint location is unconfirmed.
A question back: Where is the adapter stored (for example Hugging Face, a local path, or a specific hosting platform), and do you need to run it for inference or fine-tune it further?
- 1
Replicatereplicate.comverified and signed
Replicate runs open-source models through a cloud API, and its action record lists meta/meta-llama-3-8b-instruct, an 8 billion parameter chat-tuned Llama 3 model from Meta 212.
for agents: meta/meta-llama-3-8b-instruct · prunaai/meta-llama-3-8b · meta/meta-llama-3-8b
- 2
Sources
- 2Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 9Brev.dev Consolebrev.nvidia.com · read 2026-10-29
- 12meta/meta-llama-3-8b-instruct: declares "meta/meta-llama-3-8b-instruct" (the record we read and signed)unfragile.ai · read 2026-10-24
- 19Llama-3.1-8B-Instruct: declares "llama3.1-8b-instruct" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
create-llms · create-llms verified and signed
Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/
meta/meta-llama-3-8b-instruct · meta/meta-llama-3-8b-instruct verified and signed
An 8 billion parameter language model from Meta, fine tuned for chat completions
github · ghapi verified and signed
retrieveFineTune · OpenAI API verified and signed
Gets info about the fine-tune job. [Learn more about Fine-tuning](/docs/guides/fine-tuning)
meta/meta-llama-3-70b-instruct · meta/meta-llama-3-70b-instruct verified and signed
A 70 billion parameter language model from Meta, fine tuned for chat completions
meta/codellama-7b-instruct · meta/codellama-7b-instruct verified and signed
A 7 billion parameter Llama tuned for coding and conversation
lucataco/qwen3-vl-8b-instruct · lucataco/qwen3-vl-8b-instruct verified and signed
A powerful vision-language model in the Qwen series
meta/llama-4-maverick-instruct · meta/llama-4-maverick-instruct verified and signed
A 17 billion parameter model with 128 experts
meta/codellama-13b-instruct · meta/codellama-13b-instruct verified and signed
A 13 billion parameter Llama tuned for coding and conversation
meta/codellama-34b-instruct · meta/codellama-34b-instruct verified and signed
A 34 billion parameter Llama tuned for coding and conversation
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.