RTX 3070 8GB runs Llama 3.1 8B
speed
73.74 tok/s
setup
Q4_K_M · 4K context
Agent code task · 512 tokens · 1 recorded run
Open the receipt§ 001 / FIT RECEIPTS
What your hardware actually runs.
These are measured answers, not VRAM guesses: exact GPU, model, quant, context, workload, and observed speed.
§ 002 / MEASURED FIT RECEIPTS
Measured fit receipts
RTX 3070 8GB runs Qwen3.5 9B
speed
59.39 tok/s
setup
Q4_K_M · 4K context
Agent code task · 512 tokens · 1 recorded run
Open the receiptRTX 5090 32GB runs Gemma 4 26B-A4B
speed
198.8 tok/s
setup
Q4_K_M · 4K context
Short generation · 256 tokens · 3 recorded runs
Open the receiptRTX 5090 32GB runs Llama 3.1 8B
speed
228.9 tok/s
setup
Q4_K_M · 4K context
Short generation · 256 tokens · 3 recorded runs
Open the receipt§ 003 / WHY THESE EXIST
Why these exist
A calculator can tell you whether weights fit. A receipt tells you what happened on a real machine. Use one as a starting point, then open the desk with your own GPU and save the rig for future model drops.
Get a fit for my own card →