Sponsored by
APIMart
arcee-ai / Trinity-Nano-Preview
Model's Last Updated: May 29 2026
text-generation
Introduction of Trinity-Nano-Preview
Model Details of Trinity-Nano-Preview
Trinity Nano Preview
Trinity Nano Preview is a preview of Arcee AI's 6B MoE model with 1B active parameters. It is the small-sized model in our new Trinity family, a series of open-weight models for enterprise and tinkerers alike.
This is a chat tuned model, with a delightful personality and charm we think users will love. We note that this model is pushing the limits of sparsity in small language models with only 800M non-embedding parameters active per token, and as such may be unstable in certain use cases, especially in this preview.
This is an experimental release, it's fun to talk to but will not be hosted anywhere, so download it and try it out yourself!
Trinity Nano Preview 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
Model Details
- Model Architecture: AfmoeForCausalLM
- Parameters: 6B, 1B active
- Experts: 128 total, 8 active, 1 shared
- Context length: 128k
- Training Tokens: 10T
- License: Apache 2.0
Running our model
Transformers
Use the
main
transformers branch
git clone https://github.com/huggingface/transformers.git
cd transformers
# pip
pip install '.[torch]'
# uv
uv pip install '.[torch]'
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "arcee-ai/Trinity-Nano-Preview"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto"
)
messages = [
{"role": "user", "content": "Who are you?"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
outputs = model.generate(
input_ids,
max_new_tokens=256,
do_sample=True,
temperature=0.5,
top_k=50,
top_p=0.95
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
If using a released transformers, simply pass "trust_remote_code=True":
model_id = "arcee-ai/Trinity-Nano-Preview"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
trust_remote_code=True
)
VLLM
Supported in VLLM release 0.11.1
# pip
pip install "vllm>=0.11.1"
Serving the model with suggested settings:
vllm serve arcee-train/Trinity-Nano-Preview \
--dtype bfloat16 \
--enable-auto-tool-choice \
--reasoning-parser deepseek_r1 \
--tool-call-parser hermes
llama.cpp
Supported in llama.cpp release b7061
Download the latest llama.cpp release
llama-server -hf arcee-ai/Trinity-Nano-Preview-GGUF:q4_k_m
LM Studio
Supported in latest LM Studio runtime
Update to latest available, then verify your runtime by:
- Click "Power User" at the bottom left
- Click the green "Developer" icon at the top left
- Select "LM Runtimes" at the top
- Refresh the list of runtimes and verify that the latest is installed
Then, go to Model Search and search for
arcee-ai/Trinity-Nano-Preview-GGUF
, download your prefered size, and load it up in the chat
License
Trinity-Nano-Preview is released under the Apache-2.0 license.
Runs of arcee-ai Trinity-Nano-Preview on huggingface.co
24.5K
Total runs
0
24-hour runs
866
3-day runs
491
7-day runs
491
30-day runs
More Information About Trinity-Nano-Preview huggingface.co Model
Url of Trinity-Nano-Preview
Trinity-Nano-Preview huggingface.co Url
Provider of Trinity-Nano-Preview huggingface.co
Other API from arcee-ai
Total runs:
10.0K
Run Growth:
9.3K
Growth Rate:
92.47%
Total runs:
4.2K
Run Growth:
-6.3K
Growth Rate:
-147.69%
Total runs:
4.0K
Run Growth:
-11.3K
Growth Rate:
-278.17%
Total runs:
1.8K
Run Growth:
1.5K
Growth Rate:
82.87%
Total runs:
1.7K
Run Growth:
-860
Growth Rate:
-49.60%
Total runs:
1.7K
Run Growth:
520
Growth Rate:
34.51%
Total runs:
1.5K
Run Growth:
1.5K
Growth Rate:
98.63%
Total runs:
1.2K
Run Growth:
-106
Growth Rate:
-8.55%
Total runs:
1.1K
Run Growth:
881
Growth Rate:
81.57%
Total runs:
1.1K
Run Growth:
347
Growth Rate:
31.66%
Total runs:
1.1K
Run Growth:
57
Growth Rate:
5.42%
Total runs:
1.0K
Run Growth:
-1.8K
Growth Rate:
-174.58%
Total runs:
1000
Run Growth:
189
Growth Rate:
18.96%
Total runs:
854
Run Growth:
-813
Growth Rate:
-95.65%
Total runs:
850
Run Growth:
0
Growth Rate:
0.00%
Total runs:
766
Run Growth:
-6.3K
Growth Rate:
-820.89%
Total runs:
673
Run Growth:
474
Growth Rate:
73.72%
Total runs:
626
Run Growth:
-868
Growth Rate:
-138.66%
Total runs:
614
Run Growth:
-4.4K
Growth Rate:
-715.15%
Total runs:
528
Run Growth:
-163
Growth Rate:
-30.87%
Total runs:
508
Run Growth:
119
Growth Rate:
24.49%
Total runs:
505
Run Growth:
201
Growth Rate:
39.80%
Total runs:
503
Run Growth:
382
Growth Rate:
75.94%
Total runs:
448
Run Growth:
107
Growth Rate:
23.88%
Total runs:
408
Run Growth:
0
Growth Rate:
0.00%
Total runs:
351
Run Growth:
351
Growth Rate:
100.00%
Total runs:
281
Run Growth:
0
Growth Rate:
0.00%
Total runs:
259
Run Growth:
234
Growth Rate:
90.35%
Total runs:
258
Run Growth:
23
Growth Rate:
8.91%
Total runs:
243
Run Growth:
-1.7K
Growth Rate:
-680.25%
Total runs:
242
Run Growth:
196
Growth Rate:
80.99%
Total runs:
229
Run Growth:
-796
Growth Rate:
-349.12%
Total runs:
188
Run Growth:
-48
Growth Rate:
-28.24%
Total runs:
184
Run Growth:
135
Growth Rate:
73.77%
Total runs:
179
Run Growth:
96
Growth Rate:
53.63%
Total runs:
178
Run Growth:
106
Growth Rate:
59.55%
Total runs:
158
Run Growth:
-1
Growth Rate:
-0.63%
Total runs:
148
Run Growth:
-99
Growth Rate:
-66.89%
Total runs:
147
Run Growth:
106
Growth Rate:
75.18%
Total runs:
130
Run Growth:
65
Growth Rate:
50.00%
Total runs:
130
Run Growth:
11
Growth Rate:
9.17%
Total runs:
117
Run Growth:
51
Growth Rate:
44.35%
Total runs:
108
Run Growth:
81
Growth Rate:
77.88%
Total runs:
99
Run Growth:
86
Growth Rate:
87.76%
Total runs:
98
Run Growth:
83
Growth Rate:
85.57%
Total runs:
97
Run Growth:
87
Growth Rate:
89.69%
Total runs:
96
Run Growth:
75
Growth Rate:
79.79%
Total runs:
95
Run Growth:
70
Growth Rate:
73.68%
Total runs:
95
Run Growth:
70
Growth Rate:
76.92%
Total runs:
95
Run Growth:
79
Growth Rate:
83.16%
Total runs:
92
Run Growth:
33
Growth Rate:
35.87%
Total runs:
92
Run Growth:
35
Growth Rate:
37.63%
Total runs:
91
Run Growth:
77
Growth Rate:
85.56%
Total runs:
91
Run Growth:
78
Growth Rate:
86.67%
Total runs:
91
Run Growth:
76
Growth Rate:
84.44%
Total runs:
91
Run Growth:
77
Growth Rate:
85.56%
Total runs:
90
Run Growth:
68
Growth Rate:
73.91%
Total runs:
89
Run Growth:
80
Growth Rate:
90.91%
Total runs:
89
Run Growth:
75
Growth Rate:
86.21%
Total runs:
89
Run Growth:
70
Growth Rate:
78.65%
Total runs:
89
Run Growth:
79
Growth Rate:
89.77%
Total runs:
88
Run Growth:
80
Growth Rate:
91.95%
Total runs:
88
Run Growth:
72
Growth Rate:
81.82%
Total runs:
88
Run Growth:
71
Growth Rate:
82.56%
Total runs:
87
Run Growth:
65
Growth Rate:
75.58%
Total runs:
86
Run Growth:
75
Growth Rate:
87.21%
Total runs:
86
Run Growth:
66
Growth Rate:
77.65%
Total runs:
86
Run Growth:
78
Growth Rate:
90.70%
Total runs:
85
Run Growth:
73
Growth Rate:
85.88%
Total runs:
85
Run Growth:
69
Growth Rate:
82.14%
Total runs:
85
Run Growth:
76
Growth Rate:
90.48%
Total runs:
84
Run Growth:
71
Growth Rate:
84.52%