coja/dots
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[LLM] models update

Browse Source
This commit is contained in:
Coja
2026-09-21 17:45:07 +02:00
parent e65d8e597a
commit 9fc7854751
11 changed files with 215 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/.config/aichat/config.yaml
+5
View File
@@ -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
common/.config/misc/tuis.txt
+1
View File
@@ -12,6 +12,7 @@ btop
bandwhich
mtr
gping
flow
bmon
profanity
nmtui
common/.config/opencode/opencode.json
+4
View File
@@ -150,6 +150,8 @@
"gemma-4-26B-A4B-it-UD-IQ4_XS": { "name": "Gemma 4 26B · 24k · vision — quality generalist (~34 t/s, remote)", "attachment": true, "limit": { "context": 24576, "output": 4096 } },
"gemma-4-E4B-it-UD-Q8_K_XL": { "name": "Gemma 4 E4B · 64k · vision — fast generalist, long docs (~57 t/s, remote)", "attachment": true, "limit": { "context": 65536, "output": 16384 } },
"GLM-4.7-Flash-UD-Q4_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash · 24k — quality coder (~21 t/s, remote)", "limit": { "context": 24576, "output": 8192 } },
"GLM-4.7-Flash-UD-Q3_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s, remote)", "limit": { "context": 24576, "output": 8192 } },
"Ornith-1.5-35B-A3B-IQ3_XXS": { "reasoning": true, "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s, remote)", "attachment": true, "limit": { "context": 24576, "output": 8192 } },
"gpt-oss-20b": { "reasoning": true, "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s, remote)", "limit": { "context": 65536, "output": 8192 } },
"gpt-oss-20b-low": { "reasoning": true, "name": "gpt-oss 20B low · 64k — snappy answers (~37 t/s, remote)", "limit": { "context": 65536, "output": 8192 } }
}
@@ -171,6 +173,8 @@
"gemma-4-26B-A4B-it-UD-IQ4_XS": { "name": "Gemma 4 26B · 24k · vision — quality generalist (~34 t/s)", "attachment": true, "limit": { "context": 24576, "output": 4096 } },
"gemma-4-E4B-it-UD-Q8_K_XL": { "name": "Gemma 4 E4B · 64k · vision — fast generalist, long docs (~57 t/s)", "attachment": true, "limit": { "context": 65536, "output": 16384 } },
"GLM-4.7-Flash-UD-Q4_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash · 24k — quality coder (~21 t/s)", "limit": { "context": 24576, "output": 8192 } },
"GLM-4.7-Flash-UD-Q3_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s)", "limit": { "context": 24576, "output": 8192 } },
"Ornith-1.5-35B-A3B-IQ3_XXS": { "reasoning": true, "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s)", "attachment": true, "limit": { "context": 24576, "output": 8192 } },
"gpt-oss-20b": { "reasoning": true, "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s)", "limit": { "context": 65536, "output": 8192 } },
"gpt-oss-20b-low": { "reasoning": true, "name": "gpt-oss 20B low · 64k — snappy answers (~37 t/s)", "limit": { "context": 65536, "output": 8192 } }
}
common/.pi/agent/models.json
+40
View File
@@ -95,6 +95,26 @@
"maxTokens": 4096,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "GLM-4.7-Flash-UD-Q3_K_XL",
"name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s)",
"reasoning": true,
"compat": { "thinkingFormat": "qwen-chat-template" },
"input": ["text"],
"contextWindow": 24576,
"maxTokens": 4096,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Ornith-1.5-35B-A3B-IQ3_XXS",
"name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s)",
"reasoning": true,
"compat": { "thinkingFormat": "qwen-chat-template" },
"input": ["text", "image"],
"contextWindow": 24576,
"maxTokens": 4096,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "gpt-oss-20b",
"name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s)",
@@ -210,6 +230,26 @@
"maxTokens": 4096,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "GLM-4.7-Flash-UD-Q3_K_XL",
"name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s)",
"reasoning": true,
"compat": { "thinkingFormat": "qwen-chat-template" },
"input": ["text"],
"contextWindow": 24576,
"maxTokens": 4096,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Ornith-1.5-35B-A3B-IQ3_XXS",
"name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s)",
"reasoning": true,
"compat": { "thinkingFormat": "qwen-chat-template" },
"input": ["text", "image"],
"contextWindow": 24576,
"maxTokens": 4096,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "gpt-oss-20b",
"name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s)",