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

添加Qwen3-Coder-Next启动指令

Browse Source
This commit is contained in:
jimmychen
2026-04-19 03:22:06 -04:00
parent ae662ef32a
commit b2e3a1436e
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llama-cpp.md
View File

@@ -11,6 +11,10 @@ No thinking: --chat-template-kwargs "{\"enable_thinking\": false}"
./llama-server --model /home/jimmy/NVME/model/Qwen3.6-35B-A3B-UD-IQ4_NL.gguf --alias "Qwen3.6-35B-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 ./llama-server --model /home/jimmy/NVME/model/Qwen3.6-35B-A3B-UD-IQ4_NL.gguf --alias "Qwen3.6-35B-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
## Qwen3-Coder-Next
./llama-server --model /home/jimmy/NVME/model/Qwen3-Coder-Next-UD-IQ4_XS.gguf --alias "Qwen3-Coder-Next" --seed 3407 --temp 1.0 --top-p 0.95 --min-p 0.01 --top-k 40 --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 -t 24 -np 4 -ngl 999 --n-cpu-moe 24
## Qwen3.5 27B ## Qwen3.5 27B