Jackrong

/

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF

like 587

Hey everybody,
Please share your parameters for webdev/coding use. I use opencode, seems fine, sometime crashing opencode but not sure it's because of oh-my-openagent plugin or because of this gguf. Don't want to analyze further. But if somebody have some configs good to share, please do. This is mine:

c:\0_llama_server\llama-server ^
    -m a:\0_LM_Studio\Jackrong\Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF\Qwen3.5-27B.Q6_K.gguf ^
    -ngl 999 --threads 22 --ctx-size 196610 --alias qwen3.5:27b ^
    --flash-attn on ^
    --batch-size 1024 ^
    --ubatch-size 256 ^
    --host 0.0.0.0 ^
    --repeat_penalty 1.1 ^
    --presence_penalty 0.0 ^
    --temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.00 ^
    --port 8080 --no-context-shift  ^
    --spec-type ngram-mod --spec-ngram-size-n 24 --draft-min 48 --draft-max 64 ^
    --jinja ^
    --seed 3407 --reasoning-format deepseek --ctx-checkpoints 128 --reasoning 1