EI
Engineering Ingegneria Informatica
Language model · Italy ·Feb 2025

EngGPT2 16B-A3B

Language Open Weights
16B
Parameters

About EngGPT2 16B-A3B

EngGPT2 16B-A3B is an AI model developed by Engineering Ingegneria Informatica, in the language category, released in 2025, made available as an open-weights model with 16B params. Sparse MoE Italian LLM trained from scratch (~2.5T tokens) by Engineering (Eng)..

On this page you'll find EngGPT2 16B-A3B's full specifications. Review provider pricing and benchmark scores below, or compare EngGPT2 16B-A3B head-to-head with other language models.

→ More models by Engineering Ingegneria Informatica → All language models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run EngGPT2 16B-A3B locally — what to buy

Share this build ↗

Sized to what EngGPT2 16B-A3B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
Intel Arc B580 12GB
Consumer GPU · ~$249
~36.6 tok/s
Q4 · tight on context · up to 2k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
Intel Arc A770 16GB
Consumer GPU · ~$329
~45 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 5090
Consumer GPU · ~$1,999
~120 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
18–120+ tok/s
27 options →
Apple
27.5–73.2 tok/s
17 options →
Datacenter GPU
74.3–120+ tok/s
13 options →

Community

Would you run EngGPT2 16B-A3B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like EngGPT2 16B-A3B

AI
DMind-1
 AI
COLLECTIVE-1
 AI
Cogito 1 series
 AI
Euler (Euler大模型)
· 2.5B
 AI
SmolLM-1.7B
· 1.7B
 AI
Llama-3-70B-Synthia-v3.5
· 70B

Frequently asked questions

What is EngGPT2 16B-A3B? ▶

Sparse MoE Italian LLM trained from scratch (~2.5T tokens) by Engineering (Eng). It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created EngGPT2 16B-A3B? ▶

EngGPT2 16B-A3B was developed by Engineering Ingegneria Informatica and released in 2025.

Is EngGPT2 16B-A3B open source or proprietary? ▶

EngGPT2 16B-A3B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does EngGPT2 16B-A3B cost? ▶

Pricing for EngGPT2 16B-A3B depends on the provider. See the providers table on this page for the latest API rates.

How does EngGPT2 16B-A3B perform on benchmarks? ▶

Benchmark scores for EngGPT2 16B-A3B are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about EngGPT2 16B-A3B?