LM Studio

LM Studio. Docs checked 2026-10-12. Default documented port is 1234, not 8080.

Desktop app that both chats and serves an OpenAI-compatible API on port 1234 by default.

What it’s for

Local chat plus a /v1 others can call. Can also be the client against llama-server — check current UI; server mode is the documented OpenAI path.

Local endpoint

llama-server base: http://127.0.0.1:8080/v1
Strata base: http://127.0.0.1:8083/v1
Model name: Model identifier shown in LM Studio (not gpt-4o-mini)
API key: Optional unless you enabled auth

Tool calling

Documented OpenAI endpoints include chat completions and Responses. Tool-calling completeness on Radeon GGUF is not documented.

Long context

Set in the app / server. Do not assume 262K.

ROCm / Radeon gotchas

LM Studio’s own engine on Linux/Windows AMD is a separate stack from this site’s llama.cpp Vulkan daily driver. Prefer pointing clients at our llama-server if the in-app AMD path is unclear.

Hybrid local + cloud

Desktop is local-first; remote OpenAI-shaped APIs exist in the product — details not fully documented here.

This is the same question as the calculator’sfully localversushybridtoggle. This page does not quote cloud prices.

Official links

Sources

LM Studio — OpenAI compatibility

Copy-paste

More on the connect page. Prove http://127.0.0.1:8080/v1/models first.

LM Studio — documented server vs our :8080

# Documented OpenAI-compat path: LM Studio *serves* on port 1234.
# Other clients call: http://127.0.0.1:1234/v1
#
# Pointing LM Studio *at* our llama-server :8080 (http://127.0.0.1:8080/v1) is a current-UI check,
# not the documented server recipe.

LM Studio’s own engine on Linux/Windows AMD is a separate stack from this site’s llama.cpp Vulkan daily driver.

LM Studio — documented server vs our :8083

# Documented OpenAI-compat path: LM Studio *serves* on port 1234.
# Other clients call: http://127.0.0.1:1234/v1
#
# Pointing LM Studio *at* our Strata :8083 (http://127.0.0.1:8083/v1) is a current-UI check,
# not the documented server recipe.

LM Studio’s own engine on Linux/Windows AMD is a separate stack from this site’s llama.cpp Vulkan daily driver.