all-MiniLMon your own GPUs.

all-MiniLM for search and retrieval inside your network. Documents are embedded and ranked on your own hardware, next to the model that answers.

Start the $4,900 pilot Compare all models

22.7M

LLM_Deploy

Card no. LD-161Issued 2026-10-27sentence-transformers

all-MiniLM-L6-v2

Pilot $4,900 fixed

Sizes: 22.7M
Active params: All parameters (dense)
Context: 512 tokens
Licence: Apache 2.0
Fits on: CPU only at 4-bit, any GPU
Endpoint: llm.yourcompany.internal/v1
Egress: 0
Owner: YOU

The 72-hour pilot with all-MiniLM.

$4,900 fixed. One model, 22.7M parameters: an estimated under 0.1 GB at FP8, so it fits on CPU only at 4-bit.

Live on your data

72 h$4,900 fixed

all-MiniLM live on your data in 72 hours. The clock starts after access and prerequisites.

Your endpoint

/v1OpenAI-compatible

OpenAI-compatible endpoint. Your applications switch by changing the base URL.

Your hardware

CPU only at 4-bit, any GPU

The readout

Evalon your data

Reference evaluation on your data. Readout and production scoping.

We size the hardware and source it at cost, with no markup. Ballpark: one H100 80GB ≈ $25–30k; a 4×H100 node ≈ $180–240k; smaller models run on far less.

Same SDK. Change the base URL.

The model is one parameter. Everything else in your application stays as it is.

client = OpenAI(
    base_url="https://llm.yourcompany.internal/v1",   # inside your network
    api_key="your-key",
)
vectors = client.embeddings.create(
    model="all-minilm-l6-v2",
    input=["Clause 14.2: termination for convenience"],
)