Arcweld: Difference between revisions
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
'''Arcweld''' is a server for the primary goal of rapidly and efficiently experimenting with open weights models, with secondary goals of 1) researching novel LLM inference technologies 2) reducing the cost of using hosted APIs when it would not interfere with the primary goal. It is not intended for training since it memory bandwidth per dollar | '''Arcweld''' is a server for the primary goal of rapidly and efficiently experimenting with open weights models, with secondary goals of 1) researching novel LLM inference technologies 2) reducing the cost of using hosted APIs when it would not interfere with the primary goal. It is not intended for training since it isn't the ideal way to purchase memory bandwidth per dollar (critical for training), although it isn't forbidden. | ||
== Specifications == | == Specifications == | ||
Latest revision as of 00:33, 28 June 2025
Arcweld is a server for the primary goal of rapidly and efficiently experimenting with open weights models, with secondary goals of 1) researching novel LLM inference technologies 2) reducing the cost of using hosted APIs when it would not interfere with the primary goal. It is not intended for training since it isn't the ideal way to purchase memory bandwidth per dollar (critical for training), although it isn't forbidden.
Specifications[edit | edit source]
- Mac Studio M3 Ultra
- 819 GB/s memory bandwidth
- 60-core GPU
- 32-core Neural Engine
- 512GB Unified Memory
Setup instructions[edit | edit source]
- Download and install Tailscale
- Some VPNs are incompatible and you may need to disable them.
- Join using a Tailscale invite link
- If you've been granted login access, `ssh sparks@arcweld` to access the shared inference account. You may have to reboot for it to work.