M/R
ModelRig
Matcher
Models
Hardware
Compare
Guides
SYS: READY
Home
/
Matcher
INTERACTIVE FIT CHECK
Model × quant × device
Estimate memory fit without pretending to predict exact speed.
AI model
Llama 3.1 8B
Llama 3.3 70B
Qwen2.5 7B
Qwen2.5 14B
Qwen2.5 32B
Qwen2.5 72B
Qwen3 8B
Qwen3 14B
Qwen3 32B
DeepSeek-R1 Distill Qwen 7B
DeepSeek-R1 Distill Qwen 14B
DeepSeek-R1 Distill Qwen 32B
Gemma 3 4B
Gemma 3 12B
Gemma 3 27B
Phi-4 14B
Mistral 7B v0.3
Mistral Small 24B
Mixtral 8x7B
Codestral 22B
DeepSeek Coder 6.7B
DeepSeek Coder 33B
Yi 34B
Command R 35B
Stable Diffusion 1.5
Stable Diffusion XL
FLUX.1 Schnell
FLUX.1 Dev
Whisper Large v3
MusicGen Large
Quantization
Q4_K_M
Q5_K_M
Q8_0
FP16
Hardware
RTX 3060 12GB
RTX 3080 10GB
RTX 3090 24GB
RTX 4060 Ti 16GB
RTX 4070 Ti Super 16GB
RTX 4080 Super 16GB
RTX 4090 24GB
RTX 5060 Ti 16GB
RTX 5070 Ti 16GB
RTX 5080 16GB
RTX 5090 32GB
RTX A6000 48GB
RTX PRO 6000 Blackwell 96GB
L40S 48GB
A100 80GB
H100 80GB
Radeon RX 7900 XTX 24GB
Radeon PRO W7900 48GB
Mac mini M4 Pro 64GB
Mac Studio M4 Max 128GB
Mac Studio M3 Ultra 256GB
Framework Desktop Ryzen AI Max+ 128GB
DGX Spark 128GB
CPU workstation 128GB RAM
Context reserve
Standard / single user
Longer context
Very long context / larger batch
ESTIMATED MEMORY FIT
—
—
OPEN FULL MODEL FILE →