Unfragile

The request names L3.3-Faust-70B-exp.001, a model name rather than a platform, and none of the candidate sources describe that model. The closest matches for running a 70B Llama 3.3-class model are Replicate, which hosts an Ollama Llama 3.3 70B action 28, and Modal, a platform for deploying inference workloads at scale 511. Which hosting or runtime you prefer would change the answer.

A question back: Do you want to host L3.3-Faust-70B-exp.001 yourself, or call it through a hosted API, and which model provider or weights source are you using for it?

1
Replicatereplicate.comverified and signed
Runs open-source machine learning models through a cloud API, including an Ollama Llama 3.3 70B model wrapper 28.
Website Docs Pricing Get started
for agents: lucataco/ollama-llama3.3-70b · lucataco/ollama-llama3-70b
2
Modalmodal.comverified and signed
Cloud infrastructure for deploying and serving AI inference and training workloads at scale on custom container stacks 511.
Website Docs Pricing Get started
+20 community tools built for it
for agents: infrastructure · serverless · modal
3
LiteLLMlitellm.aifound in code, not yet checked
Open-source AI gateway that routes requests to 140+ model providers behind one OpenAI-compatible key, including self-hosted endpoints 410.
Website Docs Pricing
+8 community tools built for it
for agents: curl · shell · write_report

Sources

2Replicate - Run AI with an APIreplicate.com · read 2026-10-29
4LiteLLM — Open-Source AI Gateway & LLM Proxylitellm.ai · read 2026-10-29
5Modal: The platform for production AImodal.com · read 2026-10-29
8lucataco/ollama-llama3.3-70b: declares "lucataco/ollama-llama3.3-70b" (the record we read and signed)unfragile.ai · read 2026-10-24
10shin-watcher-oss: declares "curl" (the record we read)github.com · read 2026-10-24
11modal: declares "infrastructure" (the record we read and signed)unfragile.ai · read 2026-10-24

For agents: the 10 actions behind this answer

arize-experiment · arize-experiment verified and signed
Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model performance, evaluat
lucataco/ollama-llama3.3-70b · lucataco/ollama-llama3.3-70b verified and signed
Ollama Llama 3.3 70B
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.
meta/llama-2-70b · meta/llama-2-70b verified and signed
Base version of Llama 2, a 70 billion parameter language model from Meta.
mikeei/dolphin-2.9-llama3-70b-gguf · mikeei/dolphin-2.9-llama3-70b-gguf verified and signed
Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant.
nateraw/goliath-120b · nateraw/goliath-120b verified and signed
An auto-regressive causal LM created by combining 2x finetuned Llama-2 70B into one.
meta/codellama-70b-instruct · meta/codellama-70b-instruct verified and signed
A 70 billion parameter Llama tuned for coding and conversation
python · fastcore verified and signed
uwulewd/airoboros-llama-2-70b · uwulewd/airoboros-llama-2-70b verified and signed
Inference Airoboros L2 70B 2.1 - GPTQ using ExLlama.
spuuntries/miqumaid-v1-70b-gguf · spuuntries/miqumaid-v1-70b-gguf verified and signed
NeverSleep's MiquMaid v1 70B Miqu Finetune, GGUF Q3_K_M quantized by NeverSleep.

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.