ChatCodingAI codingReasoningMulti-purpose26B
Chat

Arcee Trinity Mini 26B

Trinity · Apache 2.0

Mixture of Experts: 26B total parameters, 3B active per token.

Arcee AI's mid-range Mixture-of-Experts reasoning model. 26B total parameters with only 3B active per token (128 experts, 8 selected + 1 shared). Trained on 10 trillion tokens via Datology partnership. Handles math, code, and agentic tasks well; fits at Q4_K_M on a 24 GB GPU. The most practical Trinity variant for consumer hardware. US-built, Apache 2.0 licensed.

Parameters
26B
Architecture
MoE (3B active)
Context
131,072 tokens
Released
2026-01-27
Engines
llama.cpp, ollama, LM Studio, vLLM
Builder Tools
Claude Code, Codex CLI, Continue, Cursor, LM Studio, Open WebUI, Windsurf

Parameters

26B

VRAM

20 GB

Context

128K

Formats

4

GPUs

38

Arcee Trinity Mini 26B (26B) requires 20 GB VRAM at recommended quality (Q5_K_M). At efficient quality (Q4_K_M), it fits in 17 GB VRAM, making it compatible with the NVIDIA RTX 4090 Laptop (150-175W). On NVIDIA Grace Blackwell Ultra GB300, expect approximately 332 tok/s at Q8_0. For the best experience, AMD AI Powerhouse ($1,818) is recommended.

Source: OwnRig methodology

VRAM (Recommended)

20 GB

Quantization

Q5_K_M

File Size

18.6 GB

Max Context

128K tokens

Primary Use

Chat

Memory

VRAM Requirements

QualityQuantizationVRAMFile Size
fullQ8_029 GB27.8 GB
recommendedQ5_K_M20 GB18.6 GB
efficientQ4_K_M17 GB15.9 GB
compressedQ3_K_M13 GB12.1 GB
Scaling

Context Length Impact

KV cache VRAM at Q5_K_M quality. Longer context = more memory.

ContextKV CacheTotal VRAM
2K205 MB20.2 GB
4K307 MB20.3 GB
8K717 MB20.7 GB
16K1.4 GB21.4 GB
32K2.7 GB22.7 GB
64K5.4 GB25.4 GBexceeds 24 GB
128K10.9 GB30.9 GBexceeds 24 GB

Compatible GPUs

38 devices
NVIDIA Grace Blackwell Ultra GB300Q8_0332 tok/sExcellent
Apple M4 Ultra (192GB)Q8_041 tok/sExcellent
NVIDIA GeForce RTX 3090Q5_K_M58 tok/sExcellent
NVIDIA GeForce RTX 4070 Ti SuperQ3_K_M64 tok/sExcellent
NVIDIA GeForce RTX 4080 SuperQ3_K_M70 tok/sExcellent
NVIDIA RTX 4090 Laptop (150-175W)Q3_K_M49 tok/sExcellent
NVIDIA GeForce RTX 4090Q5_K_M62 tok/sExcellent
NVIDIA GeForce RTX 5080Q3_K_M91 tok/sExcellent
NVIDIA GeForce RTX 5090Q8_074 tok/sExcellent
NVIDIA RTX PRO 6000 BlackwellQ8_075 tok/sExcellent
NVIDIA RTX PRO 6000 Blackwell Max-QQ8_075 tok/sExcellent
AMD Radeon RX 7900 XTXQ5_K_M59 tok/sExcellent
Apple M4 Max (128GB Unified)Q8_028 tok/sGood
Apple M4 Max (36GB Unified)Q8_028 tok/sGood
Apple M4 Max (64GB Unified)Q8_028 tok/sGood
Apple M4 Pro (24GB Unified)Q5_K_M21 tok/sGood
AMD Radeon Pro W7900Q8_036 tok/sGood
NVIDIA GeForce RTX 4060 Ti 16GBQ3_K_M27 tok/sGood
AMD Radeon RX 9070Q3_K_M60 tok/sGood
AMD Radeon RX 9060 XT 16GBQ3_K_M30 tok/sGood
NVIDIA GeForce RTX 5060 Ti 16GBQ3_K_M30 tok/sGood
Apple M4 Pro (48GB)Q8_014 tok/sAcceptable
Apple M3 Pro (18GB Unified)Q4_K_M8 tok/sNot viable
Apple M4 (16GB Unified)Q3_K_M8 tok/sNot viable
NVIDIA GeForce RTX 3060 12GBQ3_K_M5 tok/sNot viable
NVIDIA GeForce RTX 3080 10GBQ3_K_M11 tok/sNot viable
NVIDIA GeForce RTX 4070 SuperQ3_K_M7 tok/sNot viable
NVIDIA GeForce RTX 4070 Ti 12GBQ3_K_M7 tok/sNot viable
NVIDIA RTX 4080 Laptop (120-150W)Q3_K_M6 tok/sNot viable
Apple M1 (8GB Unified)Q3_K_MNot viable
Apple M1 (16GB Unified)Q3_K_MNot viable
Apple M1 Pro (16GB Unified)Q3_K_MNot viable
Apple M2 (8GB Unified)Q3_K_MNot viable
Apple M2 (16GB Unified)Q3_K_MNot viable
Apple M2 Pro (16GB Unified)Q3_K_MNot viable
Apple M3 (8GB Unified)Q3_K_MNot viable
Apple M3 (16GB Unified)Q3_K_MNot viable
AMD Radeon RX 9060 XT 8GBQ3_K_MNot viable

Showing 38 of 38 entries

Builder Context

Arcee Trinity Mini 26B is commonly used with Claude Code, Codex CLI, Continue, Cursor, LM Studio, Open WebUI, Windsurf. For an AI coding workflow, pair it with an embedding model like nomic-embed-text for local RAG.

FAQ

Frequently Asked Questions

How much VRAM does Arcee Trinity Mini 26B need?
Arcee Trinity Mini 26B requires 20 GB VRAM at recommended quality (Q5_K_M). At lower quality settings, it can fit in as little as 13 GB.
What is the best GPU for Arcee Trinity Mini 26B?
The NVIDIA Grace Blackwell Ultra GB300 delivers the best performance for Arcee Trinity Mini 26B, achieving 332 tok/s at Q8_0 with an excellent rating.
Can I run Arcee Trinity Mini 26B on an RTX 4060 Ti?
Yes. On the NVIDIA GeForce RTX 4060 Ti 16GB, Arcee Trinity Mini 26B runs at 27 tok/s (Q3_K_M, good).
What quantization should I use for Arcee Trinity Mini 26B?
For the best quality, use Q5_K_M (20 GB VRAM). If your GPU has limited VRAM, Q3_K_M (13 GB) is the most efficient option with acceptable quality.
Is Arcee Trinity Mini 26B good for coding?
Yes. Arcee Trinity Mini 26B is used with Claude Code, Codex CLI, Continue, Cursor, LM Studio, Open WebUI, Windsurf for local AI coding. For the best coding experience, pair it with an embedding model for local RAG.
All models

Data confidence: estimated. Source

VRAM requirements are calculated from model parameters and may vary by inference engine, context length, and batch size. Performance estimates are based on community benchmarks and should be verified for your specific configuration.Trinity is a trademark of its respective owner. OwnRig is not affiliated with or endorsed by the model creator.