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

HBM
WebGPUEnterprise

GPUs / NVIDIA

GTX 1660 Ti

Memory
GDDR6
Bus
192-bit
Published peak
288 GB/s
Capacity
6 GB

Measured

Read
253.9GB/s
Write
235.6GB/s
Copy
229.0GB/s
Random
2.86GB/s
Latency
277ns
Sustain
248.2GB/s

Medians of 1 verified run from 1 operator. Read reaches 88 % of the published peak.

Local AI speed

ModelParameters4-bit, tokens/s8-bit, tokens/s
Llama 3.1 8B8.03B≤ 63Does not fit
Qwen 2.5 14B14.7BDoes not fitDoes 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 6 GB configuration; the KV cache needs room on top.

Top operators

#OperatorScoreReadDate
1OP-201F6D60.2253.9 GB/s2026-09-27

Full GTX 1660 Ti leaderboard

Test your GPU