CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / Trinity-Mini-Base
From: arcee-ai <huggingface.co/arcee-ai>Newsgroups: alt.freeweights.textSubject:

Trinity-Mini-Base

Date: 2026-11-15Commit: b08c4f6Signed: 2DC28CC7B26A283B ✓

Text generation model with 26.1B parameters. Safetensors weights, 52.3 GB in all. Published by arcee-ai under OpenMDW-1.1.

26.1B params52.3GBTrinity-Mini-Basesafetensorscustom terms
FactsParams26.1BSize52.3 GBFormatssafetensorsTasktext generationLicenseOpenMDW-1.1From sourcecustom termsread terms
# custom terms: read the license before you download
$ fw get arcee-ai/Trinity-Mini-Base
# manifest sha256 5894f3ebd51c… · 52.3 GB · 40 files
$ fw verify ./Trinity-Mini-Base arcee-ai/Trinity-Mini-Base
From sourceHosted (signed)arcee-ai/Trinity-Mini-BaseLast check: 2026-11-15 03:37 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of Trinity-Mini-Base-Pre-Anneal.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
52.3 GB
Weights
52.2 GB (safetensors)
Parameters
26.1B
Formats
safetensors
Task
text generation
License
OpenMDW-1.1 (custom)
Files
40, each with a sha256
Publisher
arcee-ai
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: arcee-ai/Trinity-Mini-Base-Pre-Anneal

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 03:37 UTCpassed

Model card

From the publisher at commit b08c4f6. Shown as plain text with links; images open at the publisher.

Image: Arcee Trinity Mini

Trinity Mini Base#

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 base model pre fine tuning, and so is not suitable for chatting, and should be trained for your specific domain before use.

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 the reasoning model now at chat.arcee.ai or download here: arcee-ai/Trinity-Mini

Model Details#

  • Model Architecture: AfmoeForCausalLM
  • Parameters: 26B, 3B active
  • Experts: 128 total, 8 active, 1 shared
  • Context length: 128k
  • Training Tokens: 10T
  • License: OpenMDW-1.1

Benchmarks#

General Benchmarks#
BenchmarkScore
ARC-Challenge90.0%
CommonsenseQA79.6%
OpenBookQA89.0%
Winogrande75.9%
MMLU (5-shot)74.7%
AGI Eval English61.8%
BBH CoT (3-shot)54.2%
MMLU Pro45.6%
Math & Code Benchmarks#
BenchmarkScore
GSM8K56.6%
Minerva MATH 50051.8%
HumanEval+57.3%
MBPP+55.3%

Image: Powered by Datology

Try out our reasoning tune#

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-Base is released under the OpenMDW-1.1 license.

Files

40 files · 52.3 GBWeights 52.2 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 40 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
LICENSE2.62 KB2ab44b68365473c112f5092211a38f231cb23e50de68b75a13369adbd76a74df
README.md3.06 KBd3de3cfaf91d1aebe911690592a8283351bc402e004037aa51d1d20ba79f6f47
__init__.py141 Bcd5a281b63d67a096b2a47a9845f5dd56d6fda4f5b500ca863cd1c26c5f7851b
chat_template.jinja2.71 KBc295e73aea820982584a1f874fa71c61b1f3e6856adc6ef1d7efe339b936f2ad
config.json1.98 KBaf6a32d24c9dca2284db8bc710ed62bc4de5d2f8eea839facf95ac686ca0810c
configuration_afmoe.py4.76 KBb16e9f24f9b62db5cc5689ea0854d7cb8e433ed861716adce48eec0073e433ef
generation_config.json74 B1392e3ff01ead0a398c25ab7a4170b163c4514e09fe227ef8034ec93d51a723f
model-00001-of-00027.safetensors2.00 GB3f171de04cf3f8dc2fa24b9fc387f3801040d65e9053c6b186c21da81aa45955
model-00002-of-00027.safetensors2.00 GBe04523a495e32f10e384ce31d2630e0e99a65052b1b7437d468a99c145e1c9f1
model-00003-of-00027.safetensors2.00 GBf9723888d34ef89af85f68f9bd057e0b30b015abc49feea3fff76e2b79a7ab2c
model-00004-of-00027.safetensors2.00 GB9b1f9626c0566f8588309dbf95c4f40ba17f7db1de6f102582d0df6f80012de6
model-00005-of-00027.safetensors2.00 GB56995264c6afacec13ab4c1dc824211ac96ef1f0727d59cc1fa9548c8777c609
model-00006-of-00027.safetensors2.00 GBde972671411974c46bb5814467ba776b397c4018e6d2048b7adf501e6a85e0a0
model-00007-of-00027.safetensors2.00 GB01c0eb3541387ef92e75c06a0ed709071f06e8c8c7c52d797440d349a37db01c
model-00008-of-00027.safetensors2.00 GB2bbf2424deb08ea031723b95edbebdbf6bbb7f12bfe79f72be8aa54aa0ae203a
model-00009-of-00027.safetensors2.00 GB7de30037e86fdec71208191ea1d67215448de2f8a34471e10cf21028a9c2b352
model-00010-of-00027.safetensors2.00 GBcdd4880477e162a408a78fc2f65dff15160d049cda4404bc4b6b16f9cf887554
model-00011-of-00027.safetensors2.00 GBc3e5322cb09ff23c562a511c6cf405ff1fcff4fdf6c5396e44909ad441284094
model-00012-of-00027.safetensors2.00 GB39173f96faeb4b5c7493b61847f7a3c5821c9e605c2aa649301825a0f02555e2
model-00013-of-00027.safetensors2.00 GB29d5fe9740ca91b881126ad8a25e90bd367137d991fe8b99b5e1520674113402
model-00014-of-00027.safetensors1.99 GB704190ad0b603029578b00bec9d8259c419d617739e078e646ebb98d017e3707
model-00015-of-00027.safetensors2.00 GBb8f0b69a9815c6b071f77d631a00a85641b5b6acaf4e5ea92c3757bd7503bfea
model-00016-of-00027.safetensors2.00 GB24e4d797f39f6d25b609e509b16e5439af04379ee92a242a34ef149199bd0636
model-00017-of-00027.safetensors2.00 GB0f04f1d58c368aa18f3f58de7508213bcac85710da3e93aa35b589679f108156
model-00018-of-00027.safetensors2.00 GB592f8c0f92c55f66cd715cc1bc92d41afc0d01aa216c1adbe3b0c91b8db26c94
model-00019-of-00027.safetensors2.00 GB7776a4b2f8ebeab78eb453bf9530e5f659c203317756a6ade6b44f26795f9381
model-00020-of-00027.safetensors2.00 GB917771ab4f59879d297dc3bfb105a1f9363d9ea4313c331c6c9baf5119bfa68d
model-00021-of-00027.safetensors2.00 GB4aba6d78c4d44f45adac19f75a1d4d674706b70ca11e28ac0b1ceef33eb95fa2
model-00022-of-00027.safetensors2.00 GB63e761fbaea3746a73fe0fa3caab91b5c3cba124c22dcd6c6a2edab3d188fd3e
model-00023-of-00027.safetensors2.00 GB5875efce07ec310ea43047c89d84f9e6c976316c0148c8df6c87b7a88a0c7cbc
model-00024-of-00027.safetensors2.00 GBdf7e4ffa9c766a1442d9fbdff5ebab8a06bbf3b2ab8fc234b0134edae66253e4
model-00025-of-00027.safetensors2.00 GB7e45043ef0746ecd3d68c9edebdcab70b24788e1d72e3aa07b400adf467c2215
model-00026-of-00027.safetensors1.51 GB2fbc06b03a22fbcfae9750e69336240f06707b4e4f0d4e87fc275fabfb7fbcc3
model-00027-of-00027.safetensors820 MB88859ec8763a270907147ae2a89d366fbd549f24079ce0e3281f5af62f52a849
model.safetensors.index.json1.08 MB693f1045d7e4f0fb5646aab03f7dbb997b951e6d6e69dd08b2ca84a29f510f8b
modeling_afmoe.py26.6 KB67950e54244545ad8b6016dbfafdf0addb05c398f6afc0e77b621a5693be189c
special_tokens_map.json441 Bbea51ad2e39f89c84a4843f5c29f1680b9b7390ad349395bc0d3c63e17ada5c2
tokenizer.json14.6 MB606b0740c5d8940dbee3268e05beaa3e34f4e43bc7df153681122f8fcc78e134
tokenizer_config.json6.18 KBd2ebc762bc533613db731379589780ee72b779a3c0c454a4c3a1bbea430c6f79
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
b08c4f6038 pinned now2026-11-15 03:37 UTC40 files · 52.3 GB

Use it

# custom terms: read the license before you download
$ fw get arcee-ai/Trinity-Mini-Base
# manifest sha256 5894f3ebd51c… · 52.3 GB · 40 files
$ fw verify ./Trinity-Mini-Base arcee-ai/Trinity-Mini-Base
Terms that come with these files. OpenMDW 1.1: keep the agreement and the copyright notices with the files when you pass them on.
Custom license (custom). Read the license text first. Open this panel to show the commands once you accept its terms.
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/arcee-ai/Trinity-Mini-Base.json --dir ./Trinity-Mini-Base $ python3 fw.py verify ./Trinity-Mini-Base ./arcee-ai__Trinity-Mini-Base.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download arcee-ai/Trinity-Mini-Base --revision b08c4f6038f3a6a52bc9af36b027300d85a33ffc --local-dir ./Trinity-Mini-Base
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("arcee-ai/Trinity-Mini-Base", revision="b08c4f6038f3a6a52bc9af36b027300d85a33ffc") model = AutoModelForCausalLM.from_pretrained("arcee-ai/Trinity-Mini-Base", revision="b08c4f6038f3a6a52bc9af36b027300d85a33ffc", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve arcee-ai/Trinity-Mini-Base --revision b08c4f6038f3a6a52bc9af36b027300d85a33ffc
Run at home

License

Name
OpenMDW-1.1
Id
OpenMDW-1.1
Class
Custom terms
Redistribution
click-through
Listing
Hosted (signed)
Terms
OpenMDW 1.1: keep the agreement and the copyright notices with the files when you pass them on.
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
LICENSE
Text sha256
2ab44b68365473c112f5092211a38f231cb23e50de68b75a13369adbd76a74df
Terms gate
Yes. The commands stay folded until you open them after reading the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: arcee-ai <huggingface.co/arcee-ai>Newsgroups: alt.freeweights.textSubject: Trinity-Mini-BaseDate: 2026-11-15Commit: b08c4f6Signed: 2DC28CC7B26A283B ✓
Upstream
arcee-ai/Trinity-Mini-Base
Pinned commit
b08c4f6038f3a6a52bc9af36b027300d85a33ffc
Manifest
Trinity-Mini-Base.json · .minisig
Manifest sha256
5894f3ebd51cc87c11f57934ee4044d8a5f8f0620aba319b0f5d55ccc4e311b4
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:37 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/arcee-ai/Trinity-Mini-Base.json $ curl -O https://freeweights.allternit.com/manifests/arcee-ai/Trinity-Mini-Base.json.minisig $ minisign -Vm Trinity-Mini-Base.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

arcee-ai/Trinity-Mini-Base-Pre-Anneal · this model is a finetune of it

1 model in the catalog name this one as their parent.

Fine-tunes
1
Fine-tunes 1
Get it
Read license, then download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download arcee-ai/Trinity-Mini-Base
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. Trinity-Mini-Base.json. Provenance. Takedown history: none.
Source
huggingface.co/arcee-ai/Trinity-Mini-Base

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B