RunItLocal
Models
Hardware
Leaderboard
Calculator
New
About
Memory requirements calculator
Preset model
Custom
Llama 3.1 8B Instruct
Llama 3.3 70B Instruct
Llama 3.2 3B Instruct
Llama 4 Scout (17B active, 16 experts)
Qwen3 8B
Qwen3 14B
Qwen3 32B
Qwen3 30B-A3B (MoE)
Qwen3 235B-A22B (MoE)
Qwen2.5 Coder 32B Instruct
Gemma 3 4B
Gemma 3 12B
Gemma 3 27B
Mistral Small 3.1 24B
Mistral Nemo 12B
Phi-4 14B
DeepSeek R1 Distill Qwen 32B
DeepSeek R1 Distill Llama 70B
DeepSeek V3 / R1 671B (MoE)
Total params (B)
Active params (B, MoE)
Quantization
Q3_K_M
Q4_K_M
Q5_K_M
Q6_K
Q8_0
F16
Context (tokens)
Layers / KV heads / head dim
Hardware
NVIDIA GeForce RTX 5090
NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 3090
NVIDIA GeForce RTX 3090 Ti
NVIDIA GeForce RTX 5080
NVIDIA GeForce RTX 5070 Ti
NVIDIA GeForce RTX 5070
NVIDIA GeForce RTX 5060 Ti 16GB
NVIDIA GeForce RTX 4080 SUPER
NVIDIA GeForce RTX 4070 Ti SUPER
NVIDIA GeForce RTX 4060 Ti 8GB
NVIDIA GeForce RTX 3060 12GB
NVIDIA GeForce RTX 3080 10GB
AMD Radeon RX 7900 XTX
NVIDIA DGX Spark
Apple M4 (10-core GPU, 24GB)
Apple M4 Pro (20-core GPU, 48GB)
Apple M4 Max (40-core GPU, 128GB)
Apple M3 Max (40-core GPU, 64GB)
Apple M2 Ultra (76-core GPU, 192GB)
Apple M3 Ultra (80-core GPU, 512GB)
Apple M1 Max (32-core GPU, 64GB)
Apple M5 Max (40-core GPU, 128GB)
Apple M5 Pro (20-core GPU, 64GB)
No suitable GPU? Rent one by the hour on
Vast.ai
or
RunPod
(affiliate links).