ComfyUI Node: LLM Model Config
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
π SimpleQwenVL
Inputs
model_path STRING
mmproj_path STRING
n_ctx INT
n_batch INT
n_ubatch INT
n_gpu_layers INT
n_cpu_moe INT
n_threads INT
use_mmap BOOLEAN
use_mlock BOOLEAN
offload_kqv BOOLEAN
chat_handler
- none
- gemma4
- gemma3
- qwen35
- qwen3
- qwen25
- llava16
- llava15
- bakllava
- moondream
- minicpmv26
- minicpmv45
- glm41v
- glm46v
- granite
- lfm2vl
- lfm25vl
- paddleocr
- obsidian
- nanollava
- llama3visionalpha
- step3vl
chat_format
- none
- llama-2
- llama-3
- llama-4
- qwen
- alpaca
- vicuna
- oasst_llama
- baichuan-2
- baichuan
- openbuddy
- redpajama-incite
- snoozy
- phind
- intel
- open-orca
- mistrallite
- zephyr
- pygmalion
- chatml
- mistral-instruct
- chatglm3
- openchat
- saiga
- gemma
force_mmproj BOOLEAN
enable_thinking BOOLEAN
verbose BOOLEAN
debug BOOLEAN
type_k
- F32
- F16
- Q4_0
- Q4_1
- Q5_0
- Q5_1
- Q8_0
- Q8_1
- Q2_K
- Q3_K
- Q4_K
- Q5_K
- Q6_K
- Q8_K
- IQ2_XXS
- IQ2_XS
- IQ3_XXS
- IQ1_S
- IQ4_NL
- IQ3_S
- IQ2_S
- IQ4_XS
- I8
- I16
- I32
- I64
- F64
- IQ1_M
- BF16
- TQ1_0
- TQ2_0
- MXFP4
- NVFP4
- Q1_0
type_v
- F32
- F16
- Q4_0
- Q4_1
- Q5_0
- Q5_1
- Q8_0
- Q8_1
- Q2_K
- Q3_K
- Q4_K
- Q5_K
- Q6_K
- Q8_K
- IQ2_XXS
- IQ2_XS
- IQ3_XXS
- IQ1_S
- IQ4_NL
- IQ3_S
- IQ2_S
- IQ4_XS
- I8
- I16
- I32
- I64
- F64
- IQ1_M
- BF16
- TQ1_0
- TQ2_0
- MXFP4
- NVFP4
- Q1_0
config_override STRING
Outputs
STRING
Extension: ComfyUI_Simple_Qwen3-VL-gguf
Simple Qwen3-VL gguf LLM model loader
Authored by KLL535
Looking for a different node?
More nodes in ComfyUI_Simple_Qwen3-VL-gguf
Other π SimpleQwenVL nodes
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.