Model reference · open weights

Trinity-Large-Thinking-Block

Trinity-Large-Thinking-Block is an open-weight language model from arcee-ai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Licence fee required LLMs arcee-ai 1 variants 35 downloads/mo
Request a licence + hosting quote All served models Not on the shared API today — deployed on request.

About

What Trinity-Large-Thinking-Block is

src="https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/i-v1KyAMOWmgVGeic9WJ.png" alt="Arcee Trinity Large Thinking" style="max-width: 100%; height: auto;" Trinity-Large-Thinking-FP8-Block Introduction Trinity-Large-Thinking is a reasoning-optimized variant of Arcee AI's Trinity-Large family — a 398B-parameter sparse Mixture-of-Experts (MoE) model with approximately 13B active parameters per token, post-trained with extended chain-of-thought reasoning and agentic RL. This repository contains the FP8 block-quantized weights of Trinity-Large-Thinking (FP8 weights and activations with per-block scaling). For full model details, benchmarks, and usage guidance, see the main Trinity-Large-Thinking model card. Quantization Details - Scheme: FP8 Block (FP8 weights and activations, per-block scaling with E8M0 scale format) - Format: compressed-tensors - Intended use: High-throughput FP8 deployment with near-lossless quality, optimized for NVIDIA Hopper/Blackwell GPUs - Supported backends: DeepGEMM, vLLM CUTLASS, Triton Usage Inference tested on - 8x NVIDIA H100 80GB (tensor parallel = 8) - vLLM 0.18.0+ vLLM Supported in vLLM 0.18.0+ with DeepGEMM FP8 MoE acceleration. Serving with DeepGEMM enabled (recommended): Without DeepGEMM (falls back to CUTLASS/Triton): Transformers API Works out of the box on OpenRouter as arcee-ai/trinity-large-thinking. License Trinity-Large-Thinking-FP8-Block is released under the OpenMDW License, version 1.1 (OpenMDW-1.1). Citation If you use this model, please cite:

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerarcee-ai
TypeLanguage models
Parameters (lead)398.7B
Context256k tokens
Variants1
Runs withtransformers
Based onarcee-ai/Trinity-Large-Thinking
Released2026-04-01
Popularity35 downloads / month
Likes9
LicenceCommercial licence needed

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
Trinity-Large-Thinking-FP8-Block398.7BFP8~458.5 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys trinity-large-thinking-block for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (trinity-large-thinking-block below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"trinity-large-thinking-block","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Languages

en es fr de it pt ru ar hi ko zh

Tags

transformers safetensors afmoe text-generation reasoning agentic tool-calling thinking conversational custom_code en es fr de

Papers

Licence

Commercial licence needed

The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗

Sources

Weights & code

Want Trinity-Large-Thinking-Block on EU-owned hardware?

Request a licence + hosting quote See what’s served now

Explore

More language models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms