llamaperf

Qwen3-Coder 30B (3B active)

on NVIDIA RTX 5090 Laptop 24GB · llama.cpp · 65,536 ctx

Tone: positiveNVIDIA hardware
Nov 17, 2026
Throughput
107.0 t/s gen · 3706.5 tokens/s prompt processing (prefill)Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.
Quant
Q4_K_M (GGUF)
KV cache
Q8_0
System RAM
128 GB
VRAM reported
24 GB

Use cases

codingagentic

Summary

User reports Qwen3-Coder-30B-A3B-Instruct at 107.0 tok/s generation and 3,706.5 tok/s prefill on an RTX 5090 Laptop 24GB in an MSI Raider A18. Setup is llama.cpp with CUDA, Q4_K_M GGUF (17.28 GiB), Q8_0 KV cache, FlashAttention on, 65,536-token context, all layers on the GPU, one slot. The figures come from a repository-analysis workload with an 8,638-token prompt and 371 generated tokens; the user notes the screenshot captures one strong interval, not an average across the audit.

Compare this run

Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.

Qwen3-Coder 30B · 3B active at 4-bit by hardware

Bars are medians on one scale, 0 to 107.0 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Models most run on the NVIDIA RTX 5090 Laptop 24GB

Bars are medians on one scale, 0 to 107.0 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Everything reported on the NVIDIA RTX 5090 Laptop 24GB →Every Qwen3-Coder report →Estimate Qwen3-Coder on this card →