Model reference · open weights
Trinity-Mini-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 Mini" style="max-width: 100%; height: auto;" Trinity Mini FP8-Block This repository contains the FP8 block-quantized weights of Trinity-Mini (FP8 weights and activations with per-block scaling). Trinity Mini is an Arcee AI 26B MoE model with 3B active parameters. It is the medium-sized model in our new Trinity family, a series of open-weight models for enterprise and tinkerers alike. This model is tuned for reasoning, but in testing, it uses a similar total token count to competitive instruction-tuned models. Trinity Mini is trained on 10T tokens gathered and curated through a key partnership with Datology, building upon the excellent dataset we used on AFM-4.5B with additional math and code. Training was performed on a cluster of 512 H200 GPUs powered by Prime Intellect using HSDP parallelism. More details, including key architecture decisions, can be found on our blog here Try it out now at chat.arcee.ai Model Details Model Architecture: AfmoeForCausalLM Parameters: 26B, 3B active Experts: 128 total, 8 active, 1 shared Context length: 128k Training Tokens: 10T License: OpenMDW-1.1 Recommended settings: temperature: 0.15 topk: 50 topp: 0.75 minp: 0.06 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-Mini with near-lossless quality, optimized for NVIDIA Hopper GPUs - Supported backends: DeepGEMM, vLLM CUTLASS, Triton Benchmarks Running our model - VLLM - Transformers VLLM Supported in VLLM release 0.18.0+ with DeepGEMM FP8 MoE acceleration. Serving the model with DeepGEMM enabled: Serving without DeepGEMM (falls back to CUTLASS/Triton): Transformers Use the main transformers branch API Trinity Mini is available today on openrouter: https://openrouter.ai/arcee-ai/trinity-mini License Trinity-Mini-FP8-Block is released under the OpenMDW-1.1 license.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | arcee-ai |
|---|---|
| Type | Language models |
| Parameters (lead) | 26.1B |
| Context | 128k tokens |
| Variants | 1 |
| Runs with | transformers |
| Based on | arcee-ai/Trinity-Mini |
| Released | 2026-03-22 |
| Popularity | 447 downloads / month |
| Likes | 2 |
| 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-Mini-FP8-Block | 26.1B | FP8 | ~30 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys trinity-mini-block for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (trinity-mini-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-mini-block","messages":[{"role":"user","content":"Hello"}]}'
Details
Languages
Tags
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 ↗