jimmychen/NormalCommands
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

添加qwopus 3.5 27B启动指令

Browse Source
This commit is contained in:
jimmychen
2026-04-12 10:09:26 -04:00
parent ae152ccc4e
commit 5f7664b854
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
llama-cpp.md
View File

@@ -1,3 +1,5 @@
## Qwen3.5 35B A3B
./llama-server --model /home/jimmy/NVME/model/Qwen3.5-35B-A3B-UD-IQ4_XS.gguf --alias "Qwen3.5-35B-A3B" --temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.00 --host 0.0.0.0 --port 11434 --kv-unified --cache-type-k q8_0 --cache-type-v q8_0 --flash-attn on --fit on --ctx-size 262144 --jinja --no-mmap -t 24 -np 4 -ngl 999
context_size 128K = 131072
@@ -5,6 +7,9 @@ context_size 128K = 131072
No thinking: --chat-template-kwargs "{\"enable_thinking\": false}"
## Qwen3.5 27B
./llama-server --model /home/jimmy/NVME/model/Qwopus3.5-27B-v3-Q4_K_S.gguf --alias "Qwen3.5-35B-A3B" --temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.00 --host 0.0.0.0 --port 11434 --kv-unified --cache-type-k q8_0 --cache-type-v q8_0 --flash-attn on --fit on --ctx-size 262144 --jinja --no-mmap -t 24 -np 4 -ngl 999
## gemma 4