branch: elpa/gptel
commit 8442f493749d6187bcbac7a75fb6c77f1bda6083
Author: Andreas Roehler <[email protected]>
Commit: Karthik Chikmagalur <[email protected]>
README: Further update Groq example models
* README.org (Groq): Update list of models in the instructions for
Groq.
Signed-off-by: Andreas Roehler <[email protected]>
---
README.org | 14 ++++++--------
1 file changed, 6 insertions(+), 8 deletions(-)
diff --git a/README.org b/README.org
index 70aec7284f..70622ecfd0 100644
--- a/README.org
+++ b/README.org
@@ -760,12 +760,11 @@ Register a backend with
:stream t
:key "your-api-key" ;can be a function that returns the key
:models '(gemma-7b-it
- llama-3.1-8b-instant
- llama3-70b-8192
llama3-8b-8192
mixtral-8x7b-32768
- qwen/qwen3.6-27b
- openai/gpt-oss-120b))
+ openai/gpt-oss-20b
+ openai/gpt-oss-120b
+ qwen/qwen3.6-27b))
#+end_src
You can pick this backend from the menu when using gptel (see
[[#usage][Usage]]). Note that Groq is fast enough that you could set =:stream
nil= and still get near-instant responses.
@@ -784,12 +783,11 @@ The above code makes the backend available to select. If
you want it to be the
:stream t
:key "your-api-key"
:models '(gemma-7b-it
- llama-3.1-8b-instant
- llama3-70b-8192
llama3-8b-8192
mixtral-8x7b-32768
- qwen/qwen3.6-27b
- openai/gpt-oss-120b)))
+ openai/gpt-oss-20b
+ openai/gpt-oss-120b
+ qwen/qwen3.6-27b)))
#+end_src
#+html: </details>
