Skip to content
modelread
Ask
Browse
Devices
Connect
Docs
Methodology
Search
⌘K
My hardware
All
Loading devices…
System RAM / unified memory override
GB
Remembered on this device. Multi-GPU: search “2x”, “8x”, “node”.
Ask
Browse
Devices
Connect
Docs
Methodology
On your hardware
Search models, devices and pages
Type a model or device name.
Pages
Ask
what should I run?
Browse
best models per device
Devices
all hardware
Connect your agent
MCP · API
How the numbers work
calibration
Models
/
deepseek-ai
deepseek-ai/DeepSeek-V4-Pro
Hugging Face
1.6T params · MoE 384 experts, top-6
DeepseekV4ForCausalLM
text-generation
mit
1M trained context
805.4 GiB repo
RTX 3060 12GB
⇅
Offload
Q5_K_M
6.80 tok/s
RTX 4060 Ti 16GB
⇅
Offload
Q8_0
4.40 tok/s
RTX 4090 24GB
✕
Won't fit
IQ2XS [8u]
RTX 5090 32GB
✕
Won't fit
IQ2XS [8u]
2x RTX 3090 (48GB)
✕
Won't fit
IQ2XS [8u]
Radeon RX 7900 XTX 24GB
✕
Won't fit
IQ2XS [8u]
Apple M4 32GB
✕
Won't fit
IQ2XS [8u]
Apple M4 Pro 48GB
✕
Won't fit
IQ2XS [8u]
Apple M4 Max 128GB
✕
Won't fit
IQ2XS [8u]
Apple M3 Ultra 512GB
✕
Won't fit
IQ2XS [8u]
NVIDIA DGX Spark (GB10) 128GB
✕
Won't fit
IQ2XS [8u]
AMD Ryzen AI Max+ 395 128GB
✕
Won't fit
IQ2XS [8u]
H100 80GB SXM
✕
Won't fit
IQ2XS [8u]
NVIDIA DGX/HGX H100 8x80GB (640GB)
✓
Fits
Q2_K-XL
115 tok/s
Apple iPhone 17 Pro / Pro Max (A19 Pro) 12GB
✕
Won't fit
FP8
Samsung Galaxy S25 Ultra (Snapdragon 8 Elite) 12GB
✕
Won't fit
FP8
Raspberry Pi 5 16GB
✕
Won't fit
FP8
NVIDIA Jetson AGX Thor 128GB
✕
Won't fit
IQ2XS [8u]
My hardware
All
Loading devices…
System RAM / unified memory override
GB
Remembered on this device. Multi-GPU: search “2x”, “8x”, “node”.
Context
4K
8K
16K
32K
64K
128K
256K
1M
KV cache
f16
q8_0
q4_0