ChatCodingMulti-purpose6B
Chat

Arcee Trinity Nano 6B

Trinity · Apache 2.0

Mixture of Experts: 6B total parameters, 1B active per token.

Arcee AI's smallest Mixture-of-Experts model. 6B total parameters with only 1B active per token (128 experts, 8 selected + 1 shared). Runs on consumer GPUs, edge devices, and mobile; fits at full Q8_0 precision on any GPU with 8 GB of VRAM. Still a preview release, so expect rough edges in some workflows. US-built, Apache 2.0 licensed.

Parameters
6B
Architecture
MoE (1B active)
Context
131,072 tokens
Released
2026-01-27
Engines
llama.cpp, ollama, LM Studio
Builder Tools
Ollama, LM Studio, Open WebUI

Parameters

6B

VRAM

5.4 GB

Context

128K

Formats

4

GPUs

43

Arcee Trinity Nano 6B (6B) requires 5.4 GB VRAM at recommended quality (Q5_K_M). At efficient quality (Q4_K_M), it fits in 4.8 GB VRAM, making it compatible with the NVIDIA RTX 4060 Laptop (40-60W). On NVIDIA Grace Blackwell Ultra GB300, expect approximately 1411 tok/s at Q8_0. For the best experience, Starter AI Desktop ($582) is recommended.

Source: OwnRig methodology

VRAM (Recommended)

5.4 GB

Quantization

Q5_K_M

File Size

4.41 GB

Max Context

128K tokens

Primary Use

Chat

Memory

VRAM Requirements

QualityQuantizationVRAMFile Size
fullQ8_07.5 GB6.53 GB
recommendedQ5_K_M5.4 GB4.41 GB
efficientQ4_K_M4.8 GB3.79 GB
compressedQ3_K_M3.9 GB2.91 GB
Scaling

Context Length Impact

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

ContextKV CacheTotal VRAM
2K0 MB5.4 GB
4K102 MB5.5 GB
8K102 MB5.5 GB
16K307 MB5.7 GB
32K614 MB6 GB
64K1.2 GB6.6 GB
128K2.3 GB7.7 GB

Compatible GPUs

43 devices
NVIDIA Grace Blackwell Ultra GB300Q8_01411 tok/sExcellent
Apple M4 Max (128GB Unified)Q8_0118 tok/sExcellent
Apple M4 Max (36GB Unified)Q8_0118 tok/sExcellent
Apple M4 Max (64GB Unified)Q8_0118 tok/sExcellent
Apple M4 Pro (24GB Unified)Q8_059 tok/sExcellent
Apple M4 Pro (48GB)Q8_059 tok/sExcellent
Apple M4 Ultra (192GB)Q8_0177 tok/sExcellent
AMD Radeon Pro W7900Q8_0152 tok/sExcellent
NVIDIA GeForce RTX 3060 12GBQ8_064 tok/sExcellent
NVIDIA GeForce RTX 3080 10GBQ8_0134 tok/sExcellent
NVIDIA GeForce RTX 3090Q8_0165 tok/sExcellent
NVIDIA GeForce RTX 4060 8GBQ8_048 tok/sExcellent
NVIDIA RTX 4060 Laptop (40-60W)Q8_045 tok/sExcellent
NVIDIA GeForce RTX 4060 Ti 16GBQ8_051 tok/sExcellent
NVIDIA RTX 4070 Laptop (80-115W)Q8_045 tok/sExcellent
NVIDIA GeForce RTX 4070 SuperQ8_089 tok/sExcellent
NVIDIA GeForce RTX 4070 Ti 12GBQ8_089 tok/sExcellent
NVIDIA GeForce RTX 4070 Ti SuperQ8_0119 tok/sExcellent
NVIDIA RTX 4080 Laptop (120-150W)Q8_068 tok/sExcellent
NVIDIA GeForce RTX 4080 SuperQ8_0130 tok/sExcellent
NVIDIA RTX 4090 Laptop (150-175W)Q8_090 tok/sExcellent
NVIDIA GeForce RTX 4090Q8_0178 tok/sExcellent
NVIDIA GeForce RTX 5080Q8_0169 tok/sExcellent
NVIDIA GeForce RTX 5090Q8_0316 tok/sExcellent
NVIDIA RTX PRO 6000 BlackwellQ8_0318 tok/sExcellent
NVIDIA RTX PRO 6000 Blackwell Max-QQ8_0318 tok/sExcellent
AMD Radeon RX 7600Q8_051 tok/sExcellent
AMD Radeon RX 7900 XTXQ8_0169 tok/sExcellent
AMD Radeon RX 9070Q8_0112 tok/sExcellent
Apple M1 Pro (16GB Unified)Q8_030 tok/sExcellent
Apple M2 Pro (16GB Unified)Q8_034 tok/sExcellent
AMD Radeon RX 9060 XT 16GBQ8_056 tok/sExcellent
AMD Radeon RX 9060 XT 8GBQ8_056 tok/sExcellent
NVIDIA GeForce RTX 5060 8GBQ8_055 tok/sExcellent
NVIDIA GeForce RTX 5060 Ti 16GBQ8_057 tok/sExcellent
Apple M3 Pro (18GB Unified)Q8_032 tok/sGood
Apple M4 (16GB Unified)Q8_026 tok/sGood
Apple M2 (8GB Unified)Q5_K_M18 tok/sGood
Apple M3 (8GB Unified)Q5_K_M20 tok/sGood
Apple M3 (16GB Unified)Q8_014 tok/sGood
Apple M1 (8GB Unified)Q5_K_M9 tok/sAcceptable
Apple M1 (16GB Unified)Q8_07 tok/sAcceptable
Apple M2 (16GB Unified)Q8_012 tok/sAcceptable

Showing 43 of 43 entries

Builder Context

Arcee Trinity Nano 6B is commonly used with Ollama, LM Studio, Open WebUI. 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 Nano 6B need?
Arcee Trinity Nano 6B requires 5.4 GB VRAM at recommended quality (Q5_K_M). At lower quality settings, it can fit in as little as 3.9 GB.
What is the best GPU for Arcee Trinity Nano 6B?
The NVIDIA Grace Blackwell Ultra GB300 delivers the best performance for Arcee Trinity Nano 6B, achieving 1411 tok/s at Q8_0 with an excellent rating.
Can I run Arcee Trinity Nano 6B on an RTX 4060 Ti?
Yes. On the NVIDIA GeForce RTX 4060 Ti 16GB, Arcee Trinity Nano 6B runs at 51 tok/s (Q8_0, excellent).
What quantization should I use for Arcee Trinity Nano 6B?
For the best quality, use Q5_K_M (5.4 GB VRAM). If your GPU has limited VRAM, Q3_K_M (3.9 GB) is the most efficient option with acceptable quality.
Is Arcee Trinity Nano 6B good for coding?
Yes. Arcee Trinity Nano 6B is used with Ollama, LM Studio, Open WebUI 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.