alt.freeweights.text / Virtuoso-Small
From: arcee-ai <huggingface.co/arcee-ai>Newsgroups: alt.freeweights.textSubject:

Virtuoso-Small

Date: 2026-11-15Commit: 4d6aadcSigned: 2DC28CC7B26A283B ✓

Model with 14.8B parameters. Safetensors weights, 29.6 GB in all. Published by arcee-ai under Apache-2.0.

14.8B params29.6GBVirtuoso-Smallsafetensorspermissive
FactsParams14.8BSize29.6 GBFormatssafetensorsTasknot taggedLicenseApache-2.0From sourcepermissive
$ fw get arcee-ai/Virtuoso-Small
# manifest sha256 8270c08485e7… · 29.6 GB · 19 files
$ fw verify ./Virtuoso-Small arcee-ai/Virtuoso-Small
From sourceHosted (signed)arcee-ai/Virtuoso-SmallLast check: 2026-11-15 03:40 UTC

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

Fine-tune of Qwen2.5-14B.

Works with

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

Overview

Size
29.6 GB
Weights
29.5 GB (safetensors)
Parameters
14.8B
Formats
safetensors
Task
not tagged
License
Apache-2.0 (permissive)
Files
19, each with a sha256
Publisher
arcee-ai
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: Qwen/Qwen2.5-14B

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 03:40 UTCpassed

Model card

From the publisher at commit 4d6aadc. Shown as plain text with links; images open at the publisher.

GGUF Available Here

Virtuoso-Small#

Virtuoso-Small is the debut public release of the Virtuoso series of models by Arcee.ai, designed to bring cutting-edge generative AI capabilities to organizations and developers in a compact, efficient form. With 14 billion parameters, Virtuoso-Small is an accessible entry point for high-quality instruction-following, complex reasoning, and business-oriented generative AI tasks. Its larger siblings, Virtuoso-Medium and Virtuoso-Large, offer even greater capabilities and are available via API at models.arcee.ai.

Key Features#

  • Compact and Efficient: With 14 billion parameters, Virtuoso-Small provides a high-performance solution optimized for smaller hardware configurations without sacrificing quality.
  • Business-Oriented: Tailored for use cases such as customer support, content creation, and technical assistance, Virtuoso-Small meets the demands of modern enterprises.
  • Scalable Ecosystem: Part of the Virtuoso series, Virtuoso-Small is fully interoperable with its larger siblings, Medium and Large, enabling seamless scaling as your needs grow.

Deployment Options#

Virtuoso-Small is available under the Apache-2.0 license and can be deployed locally or accessed through an API at models.arcee.ai. For larger-scale or more demanding applications, consider Virtuoso-Medium or Virtuoso-Large.

Open LLM Leaderboard Evaluation Results#

Detailed results can be found here

MetricValue
Avg.39.43
IFEval (0-Shot)79.35
BBH (3-Shot)50.40
MATH Lvl 5 (4-Shot)34.29
GPQA (0-shot)11.52
MuSR (0-shot)14.44
MMLU-PRO (5-shot)46.57

Files

19 files · 29.6 GBWeights 29.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 19 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md4.87 KB6ba6ddf676b651514ecf24b74606793bfb2e0c85410c69f66a602643d42b877c
added_tokens.json605 B58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
config.json710 B45959a1b5b5a186dd2c7a4e463254071bae3778a51612627f4c9b031ed9d8b0e
generation_config.json117 Bfd5d7118ccc255b4cfeb696a035d106e8aeb63d4a0b335146861a53bf5fac5be
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00008.safetensors3.89 GB4ece3598089514aef89bbc48a1d6af8f608495d65bfc3f10d38f924c16cd12a5
model-00002-of-00008.safetensors4.00 GBbbae47b261b9f38a5476010ee0bf0a4191dbe4f28394102c8f32a9755d642011
model-00003-of-00008.safetensors4.00 GB5814ac58ffe3761d26f69e5d0894b1badebc5e5aa4789c1dd35b866a0402509a
model-00004-of-00008.safetensors4.00 GB76fe53f5130f4e72b666d73941a42eb481e117005e8ff978cedb77bde28ab335
model-00005-of-00008.safetensors3.98 GB2990ef770d4e33472012178dbcda5e002269f7ce65d87fea0566faf7bacd62c9
model-00006-of-00008.safetensors4.00 GB27e2e318d145dd67a63b2df8fbfd511db15dc50a8de130740ae7fba97f726fe1
model-00007-of-00008.safetensors4.00 GBbd7882e2c484d4219a2e8beec765d884c74941e798a857ae72796e4bd117983a
model-00008-of-00008.safetensors1.70 GB4b7a0deb9beaef08614b930196d00e184a389514f213d6de58aeb8ae4b15831f
model.safetensors.index.json47.5 KB7b4b616a213f09ae889be05d1b135198589496e817d793e2605d5c5b1fe3ae5d
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json7.03 MBc0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539
tokenizer_config.json7.31 KBb86e7aacf29fdb40328c9dac9804561379cf54eba6f96cb94e64b00a81c2b30a
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
4d6aadc7c9 pinned now2026-11-15 03:40 UTC19 files · 29.6 GB

Use it

$ fw get arcee-ai/Virtuoso-Small
# manifest sha256 8270c08485e7… · 29.6 GB · 19 files
$ fw verify ./Virtuoso-Small arcee-ai/Virtuoso-Small
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/arcee-ai/Virtuoso-Small.json --dir ./Virtuoso-Small $ python3 fw.py verify ./Virtuoso-Small ./arcee-ai__Virtuoso-Small.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download arcee-ai/Virtuoso-Small --revision 4d6aadc7c9ea2843dccd03c8bec54efa61475dcc --local-dir ./Virtuoso-Small

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
6ba6ddf676b651514ecf24b74606793bfb2e0c85410c69f66a602643d42b877c
Terms gate
No extra terms beyond 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: Virtuoso-SmallDate: 2026-11-15Commit: 4d6aadcSigned: 2DC28CC7B26A283B ✓
Upstream
arcee-ai/Virtuoso-Small
Pinned commit
4d6aadc7c9ea2843dccd03c8bec54efa61475dcc
Manifest
Virtuoso-Small.json · .minisig
Manifest sha256
8270c08485e78facd764de4a54b33d1760bd7902345de56e90ffa2a11996cdc4
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:40 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/arcee-ai/Virtuoso-Small.json $ curl -O https://freeweights.allternit.com/manifests/arcee-ai/Virtuoso-Small.json.minisig $ minisign -Vm Virtuoso-Small.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

Qwen/Qwen2.5-14B · this model is a finetune of it

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

Quantizations
1
Quantizations 1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download arcee-ai/Virtuoso-Small
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Virtuoso-Small.json. Provenance. Takedown history: none.

Variants

1 quantized or adapter build of Virtuoso-Small. Each has its own license check and page.

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