The request names Llama-3.2-1B-Instruct, a model to run or fine-tune rather than a product. Replicate offers a cloud API to run open-source models including Meta's Llama 3 instruct line 111, and Ollama runs open models locally or in the cloud 6. Fine-tuning a Llama-family model is also supported by Cloudflare Workers AI finetune actions 717 and by OpenAI's fine-tuning job API 14, though the latter is for OpenAI's own models.
- 1
- 2
Ollamaollama.comwebsite read, tools not yet checked
Runs open AI models locally or in the cloud on macOS, Windows and Linux, so a 1B Llama instruct model can be served on your own machine 6.
+136 community tools built for it
- 3
Cloudflare Workers AIcloudflare.comverified and signed
Offers actions to create a fine-tune and download a fine-tune asset, which covers a fine-tuning run of a hosted model 717.
official:MCP server · @cloudflare/mcp-server-cloudflareCLI · cloudflaredskill · cloudflareskill · durable-objects+259 community tools built for it
for agents: workers-ai-download-finetune-asset · workers-ai-create-finetune · workers-ai-search-model
- 4
SGLangsglang.iowebsite read, tools not yet checked
Open-source serving framework for large language models that provides fast, scalable inference across hardware platforms 10.
+2 community tools built for it
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 6Ollama · Run AI models locally and in the cloudollama.com · read 2026-10-29
- 7Cloudflare: Build for the agent eracloudflare.com · read 2026-10-29
- 10SGLang – Fast, Open-Source LLM & Multimodal Serving Frameworksglang.io · read 2026-10-29
- 11meta/meta-llama-3-70b-instruct: declares "meta/meta-llama-3-70b-instruct" (the record we read and signed)unfragile.ai · read 2026-10-24
- 14OpenAI API: declares "createFineTune" (the record we read and signed)unfragile.ai · read 2026-10-24
- 17Cloudflare API: declares "workers-ai-download-finetune-asset" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
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/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
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
llama-3.1-nemotron-70b-instruct · Llama-3.1-Nemotron-70B-Instruct verified and signed
Task: Llama-3.1-Nemotron-70B-Instruct
meta/llama-4-maverick-instruct · meta/llama-4-maverick-instruct verified and signed
A 17 billion parameter model with 128 experts
meta/codellama-7b-instruct · meta/codellama-7b-instruct verified and signed
A 7 billion parameter Llama tuned for coding and conversation
meta/codellama-70b-instruct · meta/codellama-70b-instruct verified and signed
A 70 billion parameter Llama tuned for coding and conversation
ibm-granite/granite-3.2-8b-instruct · ibm-granite/granite-3.2-8b-instruct verified and signed
Granite-3.2-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for reasoning and instruction-following capabilities.
meta/llama-4-scout-instruct · meta/llama-4-scout-instruct verified and signed
A 17 billion parameter model with 16 experts
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.