kamma/llama-runner
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

profiles

Browse Source
This commit is contained in:
Radek Davidek 2026-05-12 20:15:18 +02:00
parent 9f909192d2
commit 600295f654
2 changed files with 54 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
config.properties
View File

@ -1,7 +1,7 @@
#Llama Runner Configuration
#Wed Apr 22 16:58:54 CEST 2026
lastProfile=Exaone4
windowHeight=1281
#Tue May 12 20:14:02 CEST 2026
lastProfile=Qwen3.6-35B-A3B-UD-Q5_K_XL-FULL
windowHeight=1271
windowWidth=665
windowX=1895
windowY=118
windowY=128

56
profiles.json
View File

@ -95,13 +95,13 @@
"threads": 99,
"flashAttention": true,
"kvUnified": true,
"cacheTypeK": "turbo3",
"cacheTypeV": "turbo3",
"temperature": 0.6,
"cacheTypeK": "q8_0",
"cacheTypeV": "q8_0",
"temperature": 1.0,
"topP": 0.95,
"topK": 20,
"minP": 0.0,
"ctxSize": 131070,
"ctxSize": 131072,
"enableThinking": false,
"modelPath": "/home/kamma/models/gpt-oss-120b-F16.gguf",
"chatTemplateKwargs": "{\"enable_thinking\": true}",
@ -295,16 +295,60 @@
"kvUnified": true,
"cacheTypeK": "q8_0",
"cacheTypeV": "q8_0",
"temperature": 0.9,
"temperature": 0.7,
"topP": 0.95,
"topK": 20,
"minP": 0.0,
"ctxSize": 180000,
"ctxSize": 260000,
"enableThinking": false,
"modelPath": "/home/kamma/models/Qwen3.6-35B-A3B-UD-Q5_K_XL.gguf",
"chatTemplateKwargs": "",
"ngl": 99,
"fit": false,
"reasoning": true
},
"Qwen3.6-27B-UD-Q6_K_XL-FULL": {
"host": "0.0.0.0",
"port": 3080,
"parallel": 1,
"batchSize": 4096,
"threads": 99,
"flashAttention": true,
"kvUnified": true,
"cacheTypeK": "q8_0",
"cacheTypeV": "q8_0",
"temperature": 0.6,
"topP": 0.95,
"topK": 20,
"minP": 0.0,
"ctxSize": 180000,
"enableThinking": false,
"modelPath": "/home/kamma/models/Qwen3.6-27B-UD-Q6_K_XL.gguf",
"chatTemplateKwargs": "{\"preserve_thinking\":true,\"enable_thinking\":true}",
"ngl": 99,
"fit": false,
"reasoning": true
},
"Qwen3.6-27B-UD-Q6_K_XL-FULL-no-thinking-180k": {
"host": "0.0.0.0",
"port": 3080,
"parallel": 1,
"batchSize": 8192,
"threads": 99,
"flashAttention": true,
"kvUnified": true,
"cacheTypeK": "q8_0",
"cacheTypeV": "q8_0",
"temperature": 0.6,
"topP": 0.95,
"topK": 20,
"minP": 0.0,
"ctxSize": 180000,
"enableThinking": false,
"modelPath": "/home/kamma/models/Qwen3.6-27B-UD-Q6_K_XL.gguf",
"chatTemplateKwargs": "",
"ngl": 99,
"fit": false,
"reasoning": false
}
}