boltbeam.fyi

Qwen3-14B Q4_K_M on RTX 5090

GGUF Q4_K+Q6_K

Engines

llama.cpp

b11571 · 097cf33d9 ↗measured 2026-11-09 18:57 UTCnewer release at the time: 0.9.0

149.5 tok/s

76% of the roofline197.8 tok/s possible

now, a token
6.69 ms
floor
5.06 ms
read, a token
9.91 GB

Speed at context

128 tokens
llama.cpp151.0 tok/s of 199.2
512 tokens
llama.cpp149.5 tok/s of 197.8
Measured at short contexts only. The pink tick is the roofline at that context.

Where the time goes

Now, a token
6.69 ms
Roofline floor, a token
5.06 ms
Gap to the floor
1.63 ms
Kernels a token
–

Launch heavy: 1325 kernel launches per token

Cannot split: attn_kv Q4_K. No kernel group matched their calls and bytes

Per role ms a token. floor (bytes ÷ measured memory speed) above the floor

This run timed the whole step only, so there is no per-role split.

No kernel capture for this run.

Run rtx5090-14b-llama-batch

Tested on

GPU
RTX 5090 · 32 GB
System RAM
31 GB
CPU threads
16
Memory, measured
1710 GB/s
Temp, max
63 °C
Power
237 W mean of 600 W
SM clock
2542 MHz, throttled
Driver
595.99.02
Measured
2026-11-09 18:57 UTC · context 512 tokens · measured, in-model (nsys): 6 of 7 weight roles timed

Qwen3-14B on other GPUs