llamaperf

DeepSeek V4.1 Flash 552B (16B active)

on AMD RX 9070 XT 16GB · Strata · 1,000,000 ctx

Tone: positiveAMD hardware
Nov 2, 2026
Throughput
7.0 t/s gen
Quant
IST-DAS 1.75 bpw
System RAM
64 GB
VRAM reported
16 GB

Use cases

codingagenticlong-context

Summary

User reports DeepSeek V4.1 Flash at 1M context running on an RX 9070 XT 16GB with experts spread across VRAM, 64 GB DDR4 and an SSD, at about 7 tok/s generation. Setup is a patched Strata engine (HIP, gfx1201) with IST-DAS 1.75 bpw weights, plus a 5800X3D and PCIe 3.0 NVMe. The patch adds KV splicing and resident-only expert routing during prompt reads. Prompt reading for a ~37K-token agent system prompt took about 100 s before the patch; the user claims agent sessions now start 20x faster. A 1.2K-token prompt previously streamed 58 GB off the SSD. The splice is approximate and resident routing changes answers slightly; the user's coding suite scored 12/13 both ways.

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.

DeepSeek V4.1 Flash 552B · 16B active at 3-bit by hardware

Bars are medians on one scale, 0 to 73.4 tokens/s. Press ▶ to watch text arrive at a row's speed.

Models most run on the AMD RX 9070 XT 16GB

Bars are medians on one scale, 0 to 98.8 tokens/s. Press ▶ to watch text arrive at a row's speed.

Everything reported on the AMD RX 9070 XT 16GB →Every DeepSeek V4.1 Flash report →Estimate DeepSeek V4.1 Flash on this card →