ComfyUI Node

LLM Model Config

A ComfyUI node in 🌐 SimpleQwenVL with 20 inputs and 1 output.

By KLL535Β·Created 9 months agoΒ·Updated about a month agoΒ· 80
LLM Model Config
    • config
    β—„model_pathβ–Ί
    β—„mmproj_pathβ–Ί
    β—„n_ctx8192β–Ί
    β—„n_batch512β–Ί
    β—„n_ubatch512β–Ί
    β—„n_gpu_layers-1β–Ί
    β—„n_cpu_moe0β–Ί
    β—„n_threads8β–Ί
    β—„use_mmaptrueβ–Ί
    β—„use_mlockfalseβ–Ί
    β—„offload_kqvtrueβ–Ί
    β—„chat_handlernoneβ–Ί
    β—„chat_formatnoneβ–Ί
    β—„force_mmprojfalseβ–Ί
    β—„enable_thinkingfalseβ–Ί
    β—„verbosefalseβ–Ί
    β—„debugtrueβ–Ί
    β—„type_kF16β–Ί
    β—„type_vF16β–Ί
    β—„config_overrideβ€”β–Ί
    Category🌐 SimpleQwenVL

    Inputs (20)

    NameTypeDefaultDescription
    model_pathSTRINGPath to GGUF model file (relative to custom_nodes dir)
    mmproj_pathSTRINGPath to multimodal projector (required for vision)
    n_ctxINT8192512–1048576Context size: image_tokens + input_tokens + output_tokens <= n_ctx
    n_batchINT51232–8192Prompt processing batch. Lower = less VRAM, higher = faster.
    n_ubatchINT51232–8192Micro-batch size for advanced memory management
    n_gpu_layersINT-1-1–256Layers to GPU: -1=all, 0=CPU only. Reduce if OOM.
    n_cpu_moeINT00–128MoE experts on CPU (VRAM saver). 0 = all on GPU.
    n_threadsINT81–64CPU threads for inference. Match physical cores.
    use_mmapBOOLEANtrueMemory mapping. set True if faster model loading.
    use_mlockBOOLEANfalseLock model in RAM (prevent swap). Uses more RAM.
    offload_kqvBOOLEANtrueOffload KV Cache to GPU. Turn OFF (slow) for safe VRAM.
    chat_handlerCOMBOnoneChat template for multimodal models.
    chat_formatCOMBOnoneChat format for text-only models.
    force_mmprojBOOLEANfalseForce load mmproj even without images (preserves template for enable_thinking).
    enable_thinkingBOOLEANfalseEnable 'thinking' mode for Qwen3.5/Gemma4 (requires more output tokens).
    verboseBOOLEANfalseVerbose llama.cpp logging
    debugBOOLEANtrueOutput timing info to console
    type_kCOMBOF1634 options: F32, F16, Q4_0, Q4_1, Q5_0, Q5_1, +28
    type_vCOMBOF1634 options: F32, F16, Q4_0, Q4_1, Q5_0, Q5_1, +28
    config_overrideoptSTRINGβ€”

    Outputs (1)

    NameTypeDescription
    configSTRINGβ€”