Base Compute

company

Verified

https://basecompute.co

AI & ML interests

local AI, GPU kernels, performance optimisation, agentic research pipelines, automated research

Recent Activity

fabian-basecompute updated a model 4 days ago

basecompute/Qwen3.8-27B

fabian-basecompute published an article 5 days ago

Base Optimization Stack: From Open Weights to Frontier On-Device Inference Speed

fabian-basecompute new activity 8 days ago

basecompute/Qwen3.8-27B:What profile did these models use?

View all activity

Articles

Base Optimization Stack: From Open Weights to Frontier On-Device Inference Speed

BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal

basecompute 's models 37

basecompute/Qwen3.8-27B

Text Generation • Updated 4 days ago • 247

basecompute/Muse-Glimmer-30B

Image-Text-to-Text • Updated 14 days ago • 15 • 1

basecompute/Qwen3-0.6B

Text Generation • Updated 17 days ago • 129

basecompute/whisper-large-v3-turbo

Automatic Speech Recognition • Updated 20 days ago • 44

basecompute/whisper-large-v3

Automatic Speech Recognition • Updated 20 days ago • 31

basecompute/whisper-large-v2

Automatic Speech Recognition • Updated 20 days ago • 33

basecompute/whisper-large

Automatic Speech Recognition • Updated 20 days ago • 30

basecompute/whisper-medium.en

Automatic Speech Recognition • Updated 20 days ago • 28

basecompute/whisper-medium

Automatic Speech Recognition • Updated 20 days ago • 41

basecompute/whisper-small.en

Automatic Speech Recognition • Updated 20 days ago • 36

basecompute/whisper-small

Automatic Speech Recognition • Updated 20 days ago • 31

basecompute/whisper-base.en

Automatic Speech Recognition • Updated 20 days ago • 37

basecompute/whisper-base

Automatic Speech Recognition • Updated 20 days ago • 28

basecompute/whisper-tiny.en

Automatic Speech Recognition • Updated 20 days ago • 33

basecompute/whisper-tiny

Automatic Speech Recognition • Updated 20 days ago • 29

basecompute/gemma-3-1b-it

Text Generation • Updated 26 days ago • 45

basecompute/gemma-4-E2B-it

Text Generation • Updated 26 days ago • 36

basecompute/Llama-3.2-3B-Instruct

Text Generation • Updated 26 days ago • 31

basecompute/Llama-3.2-1B-Instruct

Text Generation • Updated 26 days ago • 37

basecompute/Qwen3-30B-A3B-Instruct-2507

Updated 27 days ago

basecompute/gemma-4-26B-A4B-it

Text Generation • Updated 29 days ago • 43

basecompute/Qwen3.6-35B-A3B

Text Generation • Updated 29 days ago • 48

basecompute/Qwen3.6-27B

Text Generation • Updated 29 days ago • 46

basecompute/Qwen3.5-35B-A3B

Text Generation • Updated 29 days ago • 45

basecompute/Qwen3.5-2B

Text Generation • Updated 29 days ago • 40

basecompute/Qwen3.6-35B-A3B-uncensored-heretic

Text Generation • Updated Jul 20 • 16

basecompute/Mistral-7B-Instruct-v0.3

Text Generation • Updated Jul 17 • 13

basecompute/Llama-3.1-8B-Instruct

Text Generation • Updated Jul 17 • 13

basecompute/Qwen3.5-2B-Base

Text Generation • Updated Jul 14 • 12

basecompute/Qwen3-4B-Thinking-2507

Updated Jul 2 • 7