Colosseum 355B Instruct

Released
2025-01-01
Last refreshed
2026-10-09
Status
Researched 179d ago
Open weightsCommercial use: restricted
Specifications
Family
Colosseum
Released
2025-01-01
Context
16K
Parameters
355B
Architecture
Decoder Only
Specialization
general
Openness
Open weights
License
Llama 3 CommunityRestricted
Weights
Unknown
Code
Unknown
Training
Pretrained
Created by
iGenius

Italian sovereign AI company.

Milan, Italy
Founded 2016
Website
Pricing

No tracked provider pricing is available yet.

Providers(1)
NVIDIA NIM

About

Flagship instruction-tuned model optimized for Italian reasoning, coding, multilingual tasks, and long-context RAG. Supports complex document analysis and regulatory compliance reasoning.

Providers(1)

Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
NVIDIA NIM--
ServerlessPartial

Available via routers & gateways(1)

NVIDIA LLM Router Blueprint

Router

NVIDIA's open-source AI blueprint for LLM routing that selects the optimal model per prompt via intent classification or neural auto-routing; deprecated in favor of NVIDIA NeMo Switchyard.

Free OSSNVIDIA NIM

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

Compare Colosseum 355B Instruct with other models

Show all 7 popular comparisonssorted by 7-day search impressions
Colosseum 355B Instruct vs MiniCPM 2B1Colosseum 355B Instruct vs Qwen3.5-9B1Colosseum 355B Instruct vs Llama 3.1 NemoGuard 8B Content Safety1Colosseum 355B Instruct vs Llama 3.1 NemoGuard 8B Topic Control1Colosseum 355B Instruct vs Llama 3.1 Swallow 8B Instruct1Colosseum 355B Instruct vs Dracarys Llama 3.1 70B Instruct1Colosseum 355B Instruct vs Sarvam 30B1