[LLM] models update
This commit is contained in:
@@ -48,6 +48,11 @@ clients:
|
||||
supports_vision: true
|
||||
- name: GLM-4.7-Flash-UD-Q4_K_XL
|
||||
max_input_tokens: 22000 # ctx 24576 · ~21 t/s — quality coder
|
||||
- name: GLM-4.7-Flash-UD-Q3_K_XL
|
||||
max_input_tokens: 22000 # ctx 24576 · ~28 t/s — fast coder (3-bit)
|
||||
- name: Ornith-1.5-35B-A3B-IQ3_XXS
|
||||
max_input_tokens: 22000 # ctx 24576 · ~32 t/s — agentic coder, thinking
|
||||
supports_vision: true
|
||||
- name: gpt-oss-20b
|
||||
max_input_tokens: 62000 # ctx 65536 · ~38 t/s — fast reasoning + tools
|
||||
- name: gpt-oss-20b-low
|
||||
|
||||
Reference in New Issue
Block a user