$HBM is live on Pons v2, Robinhood Chain.$HBM is live on Pons v2. Buy $HBM

HBM
WebGPUEnterprise

GPUs / NVIDIA

RTX 4060 Ti

Memory
GDDR6
Bus
128-bit
Published peak
288 GB/s
Capacity
8 GB

Measured

Read
249.1GB/s
Write
243.4GB/s
Copy
237.5GB/s
Random
40.4GB/s
Latency
232ns
Sustain
238.2GB/s

Medians of 2 verified runs from 2 operators. Read reaches 87 % of the published peak.

67.12 verified runs, median 70.770.7

Local AI speed

ModelParameters4-bit, tokens/s8-bit, tokens/s
Llama 3.1 8B8.03B≤ 62Does not fit
Qwen 2.5 14B14.7B≤ 34Does not fit
gpt-oss-20b21B, 3.6B activeDoes not fitDoes not fit
Mistral Small 24B24BDoes not fitDoes not fit
Qwen 2.5 32B32.5BDoes not fitDoes not fit
Llama 3.3 70B70.6BDoes not fitDoes not fit
gpt-oss-120b117B, 5.1B activeDoes not fitDoes not fit
Upper bounds: median read ÷ bytes read per token. Mixture-of-experts models read only their active experts. Fit checks weights against the 8 GB configuration; the KV cache needs room on top.

Top operators

#OperatorScoreReadDate
1OP-5C8C4570.7273.1 GB/s2026-09-27
2OP-AA2C3067.1225.2 GB/s2026-09-27

Full RTX 4060 Ti leaderboard

Test your GPU