Total runs:
24.5K
Run Growth:
491
Growth Rate:
2.01%
Sponsored by
iMean AI Trip Planner
arcee-ai / Trinity-Mini-W4A16
Model's Last Updated: Mai 29 2026
text-generation
Introduction of Trinity-Mini-W4A16
Model Details of Trinity-Mini-W4A16
Trinity Mini W4A16
This repository contains the W4A16 quantized weights of Trinity-Mini (INT4 weights, 16-bit activations).
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: Apache 2.0
-
Recommended settings:
- temperature: 0.15
- top_k: 50
- top_p: 0.75
- min_p: 0.06
Quantization Details
-
Scheme:
W4A16(INT4 weights, 16-bit activations) - Intended use: quality-preserving 4-bit deployment of Trinity-Mini
Benchmarks
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-Mini"
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-Mini"
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-ai/Trinity-Mini \
--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-Mini-GGUF:q4_k_m \
--temp 0.15 \
--top-k 50 \
--top-p 0.75
--min-p 0.06
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-Mini-GGUF
, download your prefered size, and load it up in the chat
API
Trinity Mini is available today on openrouter:
https://openrouter.ai/arcee-ai/trinity-mini
curl -X POST "https://openrouter.ai/v1/chat/completions" \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "arcee-ai/trinity-mini",
"messages": [
{
"role": "user",
"content": "What are some fun things to do in New York?"
}
]
}'
License
Trinity-Mini-W4A16 is released under the Apache-2.0 license.
Runs of arcee-ai Trinity-Mini-W4A16 on huggingface.co
144
Total runs
0
24-hour runs
20
3-day runs
15
7-day runs
15
30-day runs
More Information About Trinity-Mini-W4A16 huggingface.co Model
Url of Trinity-Mini-W4A16
Trinity-Mini-W4A16 huggingface.co Url
Provider of Trinity-Mini-W4A16 huggingface.co
Other API from arcee-ai
Updated:Mai 29 2026
Total runs:
4.3K
Run Growth:
-8.5K
Growth Rate:
-197.18%
Total runs:
4.3K
Run Growth:
-1.1K
Growth Rate:
-26.29%
Total runs:
2.5K
Run Growth:
2.3K
Growth Rate:
92.37%
Total runs:
2.4K
Run Growth:
1.3K
Growth Rate:
55.40%
Total runs:
1.8K
Run Growth:
1.5K
Growth Rate:
82.87%
Total runs:
1.8K
Run Growth:
913
Growth Rate:
51.61%
Total runs:
1.7K
Run Growth:
-860
Growth Rate:
-49.60%
Total runs:
1.5K
Run Growth:
1.5K
Growth Rate:
98.63%
Total runs:
1.5K
Run Growth:
1.5K
Growth Rate:
96.49%
Total runs:
1.5K
Run Growth:
413
Growth Rate:
27.63%
Total runs:
1.4K
Run Growth:
1.1K
Growth Rate:
76.96%
Total runs:
1.4K
Run Growth:
1.2K
Growth Rate:
88.99%
Total runs:
1.2K
Run Growth:
-106
Growth Rate:
-8.55%
Total runs:
1.0K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.0K
Run Growth:
-1.8K
Growth Rate:
-174.58%
Total runs:
1.0K
Run Growth:
820
Growth Rate:
81.11%
Total runs:
870
Run Growth:
-938
Growth Rate:
-107.82%
Total runs:
850
Run Growth:
0
Growth Rate:
0.00%
Total runs:
766
Run Growth:
-6.3K
Growth Rate:
-820.89%
Total runs:
637
Run Growth:
-937
Growth Rate:
-147.10%
Total runs:
614
Run Growth:
-4.4K
Growth Rate:
-715.15%
Total runs:
557
Run Growth:
254
Growth Rate:
45.60%
Total runs:
528
Run Growth:
-163
Growth Rate:
-30.87%
Total runs:
505
Run Growth:
201
Growth Rate:
39.80%
Total runs:
503
Run Growth:
382
Growth Rate:
75.94%
Total runs:
478
Run Growth:
458
Growth Rate:
95.82%
Total runs:
448
Run Growth:
107
Growth Rate:
23.88%
Total runs:
436
Run Growth:
404
Growth Rate:
92.66%
Total runs:
408
Run Growth:
0
Growth Rate:
0.00%
Total runs:
382
Run Growth:
147
Growth Rate:
38.48%
Total runs:
351
Run Growth:
351
Growth Rate:
100.00%
Total runs:
281
Run Growth:
0
Growth Rate:
0.00%
Total runs:
268
Run Growth:
202
Growth Rate:
75.37%
Total runs:
265
Run Growth:
-542
Growth Rate:
-204.53%
Total runs:
243
Run Growth:
-1.7K
Growth Rate:
-680.25%
Total runs:
208
Run Growth:
145
Growth Rate:
69.71%
Total runs:
181
Run Growth:
92
Growth Rate:
50.83%
Total runs:
165
Run Growth:
110
Growth Rate:
66.67%
Total runs:
158
Run Growth:
-1
Growth Rate:
-0.63%
Total runs:
148
Run Growth:
-99
Growth Rate:
-66.89%
Total runs:
135
Run Growth:
60
Growth Rate:
44.44%
Total runs:
130
Run Growth:
49
Growth Rate:
37.69%
Total runs:
117
Run Growth:
16
Growth Rate:
13.68%
Total runs:
114
Run Growth:
102
Growth Rate:
89.47%
Total runs:
111
Run Growth:
74
Growth Rate:
68.52%
Total runs:
108
Run Growth:
72
Growth Rate:
66.67%
Total runs:
107
Run Growth:
81
Growth Rate:
75.70%
Total runs:
107
Run Growth:
72
Growth Rate:
67.29%
Total runs:
103
Run Growth:
79
Growth Rate:
76.70%
Total runs:
103
Run Growth:
80
Growth Rate:
77.67%
Total runs:
102
Run Growth:
79
Growth Rate:
77.45%
Total runs:
100
Run Growth:
68
Growth Rate:
68.00%
Total runs:
100
Run Growth:
69
Growth Rate:
69.70%
Total runs:
99
Run Growth:
51
Growth Rate:
55.43%
Total runs:
97
Run Growth:
73
Growth Rate:
75.26%
Total runs:
97
Run Growth:
71
Growth Rate:
73.20%
Total runs:
96
Run Growth:
71
Growth Rate:
73.96%
Total runs:
96
Run Growth:
70
Growth Rate:
72.92%
Total runs:
96
Run Growth:
71
Growth Rate:
73.96%
Total runs:
94
Run Growth:
18
Growth Rate:
19.15%
Total runs:
94
Run Growth:
68
Growth Rate:
72.34%
Total runs:
93
Run Growth:
66
Growth Rate:
70.97%
Total runs:
93
Run Growth:
67
Growth Rate:
74.44%
Total runs:
93
Run Growth:
69
Growth Rate:
74.19%
Total runs:
93
Run Growth:
66
Growth Rate:
70.97%
Total runs:
92
Run Growth:
73
Growth Rate:
79.35%
Total runs:
92
Run Growth:
33
Growth Rate:
35.87%
Total runs:
92
Run Growth:
69
Growth Rate:
75.00%
Total runs:
91
Run Growth:
62
Growth Rate:
68.13%