The request names a specific Llama 3 8B fine-tune (SFR-Iterative-DPO-R), which none of the sources identifies directly. The closest matches are Replicate, which hosts Llama 3 8B models through its API 16, and Cloudflare Workers AI, which can run hosted models 38. Neither source confirms that this exact checkpoint is available.
A question back: Which platform or runtime do you plan to run the model on (for example a hosted API, a local GPU, or a specific cloud), and do you need this exact SFR-Iterative-DPO-R checkpoint or any Llama 3 8B fine
- 1
- 2
Cloudflare Workers AIcloudflare.comverified and signed
Runs AI models on Cloudflare's network through a run-model action and lets you search the model catalog and fetch model input and output schemas 38.
official:MCP server · @cloudflare/mcp-server-cloudflareCLI · cloudflaredskill · cloudflareskill · durable-objects+272 community tools built for it
for agents: workers-ai-search-model · workers-ai-post-run-model · workers-ai-get-model-schema
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 3Cloudflare: Build for the agent eracloudflare.com · read 2026-10-29
- 6meta/meta-llama-3-8b: declares "meta/meta-llama-3-8b" (the record we read and signed)unfragile.ai · read 2026-10-24
- 8Cloudflare API: declares "workers-ai-search-model" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
meta/meta-llama-3-8b · meta/meta-llama-3-8b verified and signed
Base version of Llama 3, an 8 billion parameter language model from Meta.
meta/meta-llama-3-70b · meta/meta-llama-3-70b verified and signed
Base version of Llama 3, a 70 billion parameter language model from Meta.
model-recommendation · model-recommendation verified and signed
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency
meta/llama-guard-3-8b · meta/llama-guard-3-8b verified and signed
A Llama-3.1-8B pretrained model, fine-tuned for content safety classification
meta/codellama-13b-instruct · meta/codellama-13b-instruct verified and signed
A 13 billion parameter Llama tuned for coding and conversation
meta/codellama-34b · meta/codellama-34b verified and signed
A 34 billion parameter Llama tuned for coding and conversation
meta/codellama-7b · meta/codellama-7b verified and signed
A 7 billion parameter Llama tuned for coding and conversation
lucataco/ollama-llama3-70b · lucataco/ollama-llama3-70b verified and signed
Cog wrapper for Ollama llama3:70b
workers-ai-search-model · Cloudflare API verified and signed
Model Search
meta/llama-4-maverick-instruct · meta/llama-4-maverick-instruct verified and signed
A 17 billion parameter model with 128 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.