BaseRTBase Compute
|
DeepSeek-V3.2-ExpDeepSeek
|
|||||
Related Products
|
||||||
About
BaseRT is a high-performance LLM inference runtime for Apple Silicon that lets developers pull models from Hugging Face, chat with them locally, or serve an OpenAI-compatible API from one CLI. Accelerated by hand-written Metal kernels, it is designed to deliver fast prefill and decode performance on M-series Macs, with published benchmarks showing up to 6.4× faster prefill than llama.cpp, 3.9× faster than MLX, and up to 1.33× faster decode. The basert CLI handles model downloading, conversion, interactive chat, serving, completion, benchmarking, inspection, and bundle signing. Its server supports chat, completions, embeddings, transcription, tool calls, continuous batching, paged KV caching, and prefix caching, while supported models can process text, vision, and audio. BaseRT uses its own .base model format with Q2–Q8 affine quantization, optional AWQ calibration, and signed bundles, and can convert GGUF, Hugging Face, and MLX checkpoints.
|
About
Introducing DeepSeek-V3.2-Exp, our latest experimental model built on V3.1-Terminus, debuting DeepSeek Sparse Attention (DSA) for faster and more efficient inference and training on long contexts. DSA enables fine-grained sparse attention with minimal loss in output quality, boosting performance for long-context tasks while reducing compute costs. Benchmarks indicate that V3.2-Exp performs on par with V3.1-Terminus despite these efficiency gains. The model is now live across app, web, and API. Alongside this, the DeepSeek API prices have been cut by over 50% immediately to make access more affordable. For a transitional period, users can still access V3.1-Terminus via a temporary API endpoint until October 15, 2025. DeepSeek welcomes feedback on DSA via its feedback portal. In conjunction with the release, DeepSeek-V3.2-Exp has been open-sourced: the model weights and supporting technology (including key GPU kernels in TileLang and CUDA) are available on Hugging Face.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
AI infrastructure engineers who need fast, private local model inference and an OpenAI-compatible backend for applications and coding agents
|
Audience
Researchers and AI engineers looking for a solution providing a model that performs well on long-context tasks with reduced compute cost
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
Free
Open source
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationBase Compute
Founded: 2026
Australia
www.basecompute.co/getbasert
|
Company InformationDeepSeek
Founded: 2023
China
deepseek.com
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
|
|||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Hugging Face
DeepSeek
Gemma 3
Gemma 4
Llama 3.1
Llama 3.2
Mistral AI
OpenAI
Phi-3
Qwen3
|
Integrations
Hugging Face
DeepSeek
Gemma 3
Gemma 4
Llama 3.1
Llama 3.2
Mistral AI
OpenAI
Phi-3
Qwen3
|
|||||
|
|
|