SAVRN
Search Contact SAVRN

Open-weight model

answerai-colbert-small-v1

by Answer.AI answerdotai/answerai-colbert-small-v1

answerai-colbert-small-v1 is a new, proof-of-concept model by Answer.AI, showing the strong performance multi-vector models with the new JaColBERTv2.5 training recipe and some extra tweaks can reach, even with just 33 million parameters.

Parameters33M
Context512
Weights893.9 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads739.5k

Runs On

What it takes to serve answerai-colbert-small-v1 (33M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 0.1 GB 0.1 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.0 GB 0.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.0 GB 0.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

SAVRN's Notes on answerai-colbert-small-v1

We keep answerai-colbert-small-v1 on the list for one reason: it is the retrieval piece that picks which passages a larger model reads, and it costs almost nothing to host. Thirty-three million parameters stored as float32 come to 894.9 MB on disk and 0.1 GB of memory at 16-bit, so it shares a card with whatever generator it feeds. The cheapest single-card setup in our figures is one MI300X with 192 GB at $1.85 an hour, which this model barely touches. The 512-token context is the constraint: passages get chunked to fit, so the indexing pipeline matters more than the GPU.

Because the license is Apache 2.0, with an express patent grant on top of commercial use and redistribution, it is the kind of model we are comfortable embedding in a product. Two things to check: Answer.AI calls this a proof of concept, and it ships as safetensors and ONNX, so match the format to your serving stack.

Model Card

By Answer.AI, published under apache-2.0, revision 934fa8bb4ce2.

answerai-colbert-small-v1 is a new, proof-of-concept model by Answer.AI, showing the strong performance multi-vector models with the new JaColBERTv2.5 training recipe and some extra tweaks can reach, even with just 33 million parameters.

While being MiniLM-sized, it outperforms all previous similarly-sized models on common benchmarks, and even outperforms much larger popular models such as e5-large-v2 or bge-base-en-v1.5.

For more information about this model or how it was trained, head over to the announcement blogpost.

Usage

This model was designed with the upcoming RAGatouille overhaul in mind. However, it's compatible with all recent ColBERT implementations!

Sentence Transformers

This model can be used with Sentence Transformers as a multi-vector (ColBERT-style late interaction) retriever via the MultiVectorEncoder:

pip install "sentence-transformers>=6.0.0"

Read the full model card (691 words)

Configuration

Architecture
HF_ColBERT
Context length (tokens)
512
Layers
12
Hidden size
384
Feed-forward size
1,536
Attention heads
12
Vocabulary size
30,522
Stored precision
float32
Model type
bert

Identity and Version

Repository
answerdotai/answerai-colbert-small-v1
Publisher
Answer.AI
Task
Not stated by the source
Modality
Other
Library
sentence-transformers
Parameters
33M parameters
Languages
en
Revision
934fa8bb4ce2284f4c2baa232d81aca4d076fa5e
First published
2024-08-12
Last updated
2026-08-17

Files and Weights

21 files, 894.9 MB in total. The weights are 12 files totalling 893.9 MB in onnx, safetensors.

Weights12 files · 893.9 MB
Configuration3 files · 2.2 KB
Tokenizer3 files · 944.1 KB
Documentation1 file · 7.8 KB
Other1 file · 2.2 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.onnxWeights133.3 MB bd4bee8b055e
model.safetensorsWeights133.6 MB 35bb6ef696cc
model_int8.onnxWeights33.9 MB de45baeaa7a4
onnx/model.onnxWeights133.2 MB b078342c7af0
onnx/model_bnb4.onnxWeights60.2 MB 9b664122c834
onnx/model_fp16.onnxWeights66.7 MB 2165cdb0057d
onnx/model_int8.onnxWeights34.0 MB 250889c55509
onnx/model_q4.onnxWeights61.5 MB 9e8a2fcc60df
onnx/model_q4f16.onnxWeights36.2 MB a5286e7efbc2
onnx/model_quantized.onnxWeights34.0 MB 250889c55509
onnx/model_uint8.onnxWeights34.0 MB fb1967fe95a4
vespa_colbert.onnxWeights133.3 MB 9161e64cab96
config.jsonConfiguration702 B
onnx_config.jsonConfiguration767 B
special_tokens_map.jsonConfiguration695 B
README.mdDocumentation7.8 KB
artifact.metadataOther2.2 KB
.gitattributesRepository1.5 KB
tokenizer.jsonTokenizer711.4 KB
tokenizer_config.jsonTokenizer1.2 KB
vocab.txtTokenizer231.5 KB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
893.9 MB
Download from Answer.AI

Released by Answer.AI through its official repository on Hugging Face. Read the license.

Built From

  • Described by arXiv:2407.20750

Memory Requirements

PrecisionWeights in memory
As published893.9 MB
16-bit0.1 GB
8-bit0.0 GB
4-bit0.0 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About answerai-colbert-small-v1

How much GPU memory does answerai-colbert-small-v1 need?

About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (33M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run answerai-colbert-small-v1 on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use answerai-colbert-small-v1 commercially?

Yes. answerai-colbert-small-v1 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

What is answerai-colbert-small-v1's context length?

512 tokens, from the maximum position embeddings in its published configuration.