Local AI Hub
LLM Configs
LLM Runner AIO
Rankings
Coding Agents
LLM Runners
LLM Web UI
Multimodal
☕
Support
Google
GitHub
Back
Share Config
Share your local LLM configuration with the community
Platform
CUDA
MLX
ROCm
Vulkan
Multi-GPU
GPU VRAM (GB)
4
6
8
12
16
24
32
64
96
128+
System RAM (GB)
8
16
24
32
48
64
96
128+
Hardware Model
Model Name
LLM Runner
Select runner...
llama.cpp
Ollama
LM Studio
KoboldCPP
llamafile
vLLM
MLX
Jan
Text Generation WebUI
ExLlamaV2
GPTQ.cpp
WebLLM
Custom
Quantization
Q4_0
Q4_K_M
Q4_K_S
Q5_0
Q5_K_M
Q6_K
Q8_0
F16
F32
Custom
Context Size
KV Cache
F16
Q8_0
Q4_0
Q5_0
Q5_1
Custom
PP Speed (tokens/sec)
TG Speed (tokens/sec)
General Settings
Note (optional)
Share Config