AxForge offering · Request
Meta's small Llama 3.2 models (1B and 3B instruction-tuned) for fast, cheap text tasks that do not need a large model: classification, extraction, summaries, on-device style workloads on a server. Validated on AxForge hardware with a dedicated DGX Spark deployment option for your traffic only, subject to confirmed availability, configuration and licence, as an OpenAI-compatible endpoint on hardware only you use, operated by AxForge in the EU.
Currently request-only. Add your request to the public forum; this is not a booking or a promised launch.
Why AxForge
| Small, fast, cheap | 1B and 3B parameters: thousands of requests per hour on a single dedicated machine, with latency a large model cannot match. |
|---|---|
| The right size for the job | Routing, tagging, extraction, short summaries, guardrails: the tasks where a small model at high volume beats a big one at any price. |
| Same endpoint as the big ones | For an agreed deployment, subject to availability: OpenAI-compatible on your own hardware, so the small model slots into a pipeline next to Llama 3.1 or Qwen without a different SDK. |
Specifications
| Model | Llama 3.2 by meta-llama |
|---|---|
| Modalities | Text |
| Sizes | 1.2B, 3.2B |
| Licence | Open, with conditions (llama3.2); AxForge deploys under it and tells you what applies |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory), owned and operated by AxForge |
| Rental term | Hour, week, month or year |
| Hardware pricing | €1.19/hour on demand · €0.95/hour by the week · €0.91/hour by the month · €0.85/hour by the year |
| Managed service | Quoted per deployment |
| Region | Málaga, Spain (eu-es-1) |
Llama 3.2 catalogue reference: specifications and requirements. List prices in EUR.
How it works
| 1 | Add a public request describing your workload, context needs and preferred rental term. A request does not reserve hardware or promise a deployment. |
|---|---|
| 2 | If AxForge can offer a deployment, agree the configuration, hardware rental, licence and managed-service price in writing before anything is billed. |
| 3 | Only after availability and terms are confirmed would AxForge provision the agreed dedicated system and model build. |
| 4 | After provisioning, point your OpenAI SDK at your own endpoint with the model name you receive. |
| 5 | After provisioning, adjust the term (hour, week, month or year) as your workload settles. |
Request model or sign in to start.
FAQ
This page describes the managed deployment option. Availability, the model build, hardware, licence and price must be agreed before a deployment can be offered. A public request does not provision or reserve a machine. Check the console for the current serverless offering list.
High-volume, low-latency text tasks: classification, extraction, routing, short summaries and guardrails. For general chat quality look at Llama 3.1 or Qwen3.
Yes, a dedicated DGX Spark has room for a small model next to a large one; AxForge would configure both behind your endpoint. Any deployment depends on confirmed availability, configuration, licence and price.
AxForge publishes only numbers it measures itself, and has not benchmarked this model on its nodes yet. For quality benchmarks, see the official model card.
For a deployment agreed after availability is confirmed: Hardware by the hour, week, month or year; the managed service is quoted per deployment. Both are confirmed in writing before anything is billed.