Nodes/ComfyUI-Qwen3.5/Qwen 3.5 (GGUF)
ComfyUI Node

Qwen 3.5 (GGUF)

A ComfyUI node in Qwen3.5 with 15 inputs and 2 outputs.

By workordie·Created 5 months ago·Updated 5 months ago· 38
Qwen 3.5 (GGUF)
  • image
  • RESPONSE
  • THINKING
modelQwen3.5-9B
quantizationQ4_K_XL
promptDescribe this image in detail.
system_prompt
max_tokens4096
temperature0.70
top_p0.80
top_k20
repeat_penalty1.00
n_gpu_layers99
ctx_size8192
enable_thinkingfalse
seed1
cli_path
CategoryQwen3.5

Inputs (15)

NameTypeDefaultDescription
modelCOMBOQwen3.5-9BModel size. 0.8B ~1GB, 2B ~2GB, 4B ~3GB, 9B ~6GB, 27B ~17GB (Q4)
quantizationCOMBOQ4_K_XLGGUF quantization. XL = Unsloth Dynamic (smart mixed precision)
promptSTRINGDescribe this image in detail.Text prompt for the model
system_promptSTRINGOptional system prompt to set model behavior
max_tokensINT409664–32768Maximum tokens to generate
temperatureFLOAT0.700–2Sampling temperature (0.6-0.7 recommended for captioning)
top_pFLOAT0.800–1Nucleus sampling threshold
top_kINT201–100Top-K sampling
repeat_penaltyFLOAT1.000.5–2Penalty for repeated tokens
n_gpu_layersINT99-1–200-1 or 99 offloads all layers to GPU
ctx_sizeINT81921024–131072Context window size in tokens
enable_thinkingBOOLEANfalseEnable thinking mode. Outputs reasoning in THINKING output.
seedINT11–4294967295Random seed for reproducibility
imageoptIMAGEImage for vision tasks
cli_pathoptSTRINGPath to llama-mtmd-cli binary. Auto-detected if empty.

Outputs (2)

NameTypeDescription
RESPONSESTRING
THINKINGSTRING