From c233d06dcb4d4c6badaf06b42c794a1af26260dd Mon Sep 17 00:00:00 2001 From: Davide Polonio Date: Fri, 10 Apr 2026 16:10:04 +0200 Subject: [PATCH] feat(llama-swap): add 128k max-ctx profiles for qwen3.5 variants --- ollama/llama-swap.yaml | 45 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/ollama/llama-swap.yaml b/ollama/llama-swap.yaml index 5bae4af..6d4af4d 100644 --- a/ollama/llama-swap.yaml +++ b/ollama/llama-swap.yaml @@ -60,6 +60,51 @@ models: --cache-type-v q8_0 --temp 0.6 --top-p 0.95 + "qwen3.5:9b-128k": + cmd: | + /app/llama-server + --host 0.0.0.0 --port ${PORT} + --model /models/Qwen3.5-9B-Q4_K_M.gguf + --mmproj /models/Qwen3.5-9B-mmproj-F16.gguf + --alias qwen3.5:9b-128k + --n-gpu-layers 999 + --ctx-size 131072 + --flash-attn on + --jinja + --cache-type-k q8_0 + --cache-type-v q8_0 + --temp 0.7 --top-p 0.9 + + "qwen3.5:9b-uncensored-128k": + cmd: | + /app/llama-server + --host 0.0.0.0 --port ${PORT} + --model /models/HauhauCS-Qwen3.5-9B-Uncensored-Aggressive.q4_k_m.gguf + --mmproj /models/HauhauCS-Qwen3.5-9B-Uncensored-Aggressive.mmproj.gguf + --alias "hf.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:q4_k_m" + --n-gpu-layers 999 + --ctx-size 131072 + --flash-attn on + --jinja + --cache-type-k q8_0 + --cache-type-v q8_0 + --temp 0.7 --top-p 0.9 + + "qwen3.5:9b-claude-4.6-opus-reasoning-128k": + cmd: | + /app/llama-server + --host 0.0.0.0 --port ${PORT} + --model /models/Jackrong-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2.q4_k_m.gguf + --mmproj /models/Jackrong-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2.mmproj.gguf + --alias "hf.co/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF:q4_k_m" + --n-gpu-layers 999 + --ctx-size 131072 + --flash-attn on + --jinja + --cache-type-k q8_0 + --cache-type-v q8_0 + --temp 0.6 --top-p 0.95 + "gemma4:e4b-uncensored": cmd: | /app/llama-server