Model reference · open weights
Trinity-Large-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.
About
src="https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/i-v1KyAMOWmgVGeic9WJ.png" alt="Arcee Trinity Large" style="max-width: 100%; height: auto;" Trinity-Large-Preview-FP8-Block Introduction Trinity-Large-Preview is a 398B-parameter sparse Mixture-of-Experts (MoE) model with approximately 13B active parameters per token. It is the largest model in Arcee AI's Trinity family, trained on more than 17 trillion tokens and delivering frontier-level performance with strong long-context comprehension. Trinity-Large-Preview is a lightly post-trained model based on Trinity-Large-Base. This repository contains the FP8 block-quantized weights of Trinity-Large-Preview (FP8 weights and activations with per-block scaling). Try it at chat.arcee.ai More details on the training of Trinity Large are available in the technical report. 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 of Trinity-Large-Preview with near-lossless quality, optimized for NVIDIA Hopper/Blackwell GPUs - Supported backends: DeepGEMM, vLLM CUTLASS, Triton Model Variants The Trinity Large family consists of four checkpoints from the same training run: - Trinity-Large-Preview: Lightly post-trained, chat-ready model undergoing active RL - Trinity-Large-Thinking: Reasoning-optimized, agentic post-training with extended chain-of-thought - Trinity-Large-TrueBase: 10T-token pre-anneal pretraining checkpoint - Trinity-Large-Base: Full 17T-token pretrained foundation model with mid-training anneals Architecture Trinity-Large-Preview uses a sparse MoE configuration designed to maximize efficiency while maintaining large-scale capacity. Benchmarks Training Configuration Pretraining - Training tokens: 17 trillion - Data partner: Datology Posttraining - This checkpoint was instruction tuned on 20B tokens. Infrastructure - Hardware: 2,048 NVIDIA B300 GPUs - Parallelism: HSDP + Expert Parallelism - Compute partner: Prime Intellect Usage Running our model - VLLM - Transformers - API Inference tested on - 8x NVIDIA H100 80GB (tensor parallel = 8) - vLLM 0.18.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | arcee-ai |
|---|---|
| Type | Language models |
| Parameters (lead) | 398.7B |
| Context | 256k tokens |
| Variants | 1 |
| Runs with | transformers |
| Based on | arcee-ai/Trinity-Large-Preview |
| Released | 2026-03-24 |
| Popularity | 23 downloads / month |
| Likes | 3 |
| Licence | Commercial licence needed |
How it works
Variants
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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Trinity-Large-Preview-FP8-Block | 398.7B | FP8 | ~458.5 GB | — | Weights ↗ |
Using it via the API
Once AxForge deploys trinity-large-block for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (trinity-large-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-block","messages":[{"role":"user","content":"Hello"}]}'
Licence
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 ↗