Trinity Mini 26B-A3B
By Arcee AI · United States
Updated 2026-07-13
Overview
Arcee AI's US-built MoE with 3B active parameters out of 26B total. Apache-licensed, fast in practice, and tuned for agent-style workloads.
When to pick this model
- Agent frameworks needing fast, capable open models
- Enterprise deployments preferring US-based vendors
- Single-GPU inference with 128k context
- Apache-licensed MoE for commercial products
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 15 GB |
| Q5_K_M | 18 GB |
| Q8_0 | 28 GB |
| FP16 (no quantization) | 52 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, Trinity Mini 26B-A3B needs a 16 GB card at Q4_K_M (15 GB). Stepping up to Q8_0 nearly doubles the footprint to 28 GB, and unquantized FP16 weights take 52 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Trinity Mini 26B-A3B needs roughly 24 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 15 tokens/sec on entry-level GPUs, on the order of 40 tokens/sec on a mid-range card, and up to 100 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Trinity Mini 26B-A3B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for Trinity Mini 26B-A3B |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 15 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Does not fit — needs 15 GB at Q4_K_M |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Q4_K_M (15 GB used) |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Q5_K_M (18 GB used) |
| 32 GB | RTX 5090 | Q8_0 (28 GB used) |
Which GPU should you buy to run Trinity Mini 26B-A3B?
To run Trinity Mini 26B-A3B locally at Q4, you need ~15 GB of VRAM. The best value for this is a RTX 5070 Ti (16 GB VRAM).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Strengths
- Efficient MoE with around 3.5B active parameters
- 131k context window
- Tuned for agent and tool-use workflows
- Apache 2.0
Limitations
- Limited public benchmark coverage
- Less name recognition than Mistral or Qwen
- Smaller fine-tune ecosystem
Typical workloads
In our catalog grid, Trinity Mini 26B-A3B is filed under Compact MoE, Efficient Chat — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: everyday chat, drafting and summarization.
The 128k-token context window is large enough to hold entire codebases' worth of files or long reports in a single prompt, which is what makes local RAG and document analysis practical. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.
Architecture & training
Architecture: MoE · 26B total / 3.5B active · Arcee AI · 131k context
Training: Arcee AI — compact MoE for agents and enterprise.
A solid US-built MoE for agent work — worth a serious look if you value Apache licensing and a domestic vendor.
Quick start
ollama pull hf.co/arcee-ai/Trinity-Mini-26B-GGUFOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Similar models worth comparing
Frequently asked questions
How much VRAM does Trinity Mini 26B-A3B need?
At the recommended Q4_K_M quantization, Trinity Mini 26B-A3B needs about 15 GB of VRAM. Q8_0 takes 28 GB, and unquantized FP16 weights take 52 GB.
Can Trinity Mini 26B-A3B run without a GPU?
Yes — with roughly 24 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does Trinity Mini 26B-A3B support?
Trinity Mini 26B-A3B supports a 128k-token context window (131,072 tokens).
Can I use Trinity Mini 26B-A3B commercially?
Yes. Trinity Mini 26B-A3B is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.
How fast is Trinity Mini 26B-A3B on consumer hardware?
Our compatibility engine estimates on the order of 40 tokens/sec on a mid-range GPU and up to 100 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Trinity Mini 26B-A3B should I download first?
Start with Q4_K_M (15 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. On a 24 GB card you can run up to Q5_K_M.