llamaperf

Qwopus3.8 27B Coder-Flash

on 2× AMD Radeon AI PRO R9700 32GB · llama.cpp · 262,144 ctx

Tone: positiveAMD hardware
Nov 22, 2026
Throughput
26.5-68.4 t/s gen · 269-1009 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
Q5_K_M (GGUF)
KV cache
q8_0
System RAM
64 GB

Use cases

codingagentictool-use

Summary

User reports a 10.4-hour unattended agentic-coding run with Qwopus3.8-27B-Coder-Flash on a Radeon AI PRO R9700 32GB and Tiel-Coder-35B-A3B-MTP on an RX 9070 XT 16GB, generating 549K tokens from 46.8M prompt tokens. Setup is llama.cpp (Vulkan for the 27B at Q5_K_M with 262,144 context, ROCm 10.2 for the MoE at UD-IQ3_XXS with 196,608 context), q8_0 KV cache, MTP speculative decoding with up to 3 draft tokens, all layers on GPU. Overall generation was 41.1 t/s for the 27B and 43.1 t/s for the MoE; median per-request generation was 44.6 t/s (26.5 to 68.4) and 58.4 t/s (21.5 to 102.1). Overall prompt processing was 656 t/s and 616 t/s, with medians of 660 t/s (269 to 1,009) and 711 t/s (374 to 868). MTP draft acceptance averaged 0.689 and 0.831. The 27B used about 28.5 GB of the R9700's 32 GB at 262K context and stayed usable at about 30 t/s at 190K context. In a separate short-context benchmark the 27B ran about 69 t/s on Vulkan versus about 61 t/s on ROCm, and the MoE about 135 t/s on ROCm versus about 63 t/s on Vulkan.

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.

Models most run on the AMD Radeon AI PRO R9700 32GB

Bars are medians on one scale, 0 to 149.2 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 AMD Radeon AI PRO R9700 32GB →Every Qwopus3.8 report →Estimate Qwopus3.8 on this card →