AMD Ryzen AI Max+ (Strix Halo) iGPU vs Qualcomm Dragonwing IQ-9075 EVK
No like-for-like comparison yet: both have published results, but model size or batch differ. Treat the numbers below as indicative only.
| AMD Ryzen AI Max+ (Strix Halo) iGPU | Qualcomm Dragonwing IQ-9075 EVK | |
|---|---|---|
| Best LLM generation | 54.38 tok/s C 2026-10-10 (page last edited) | n/a |
| Power | 120 W spec | n/a |
| Perf / W | 0.453 tok/s/W spec | n/a |
| Price | $3999 list | n/a |
| Workloads with data | 1 of 7 | 6 of 7 |
Best published LLM generation result per platform. n/a = not published; never estimated.
Show data — all workloads, sources and like-for-like groups
object detection
Only Qualcomm Dragonwing IQ-9075 EVK has published object detection results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Qualcomm Dragonwing IQ-9075 EVK | 674 FPS inference_time · b=1 | yolov8_det / YOLOv8-Detection w8a8 · Qualcomm AI Hub tflite (QAIRT 2.50.0.260828221209) · unknown | D | unknown power n/a no power published | Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published) |
AMD Ryzen AI Max+ (Strix Halo) iGPU:
No published object detection results for AMD Ryzen AI Max+ (Strix Halo) iGPU or Qualcomm Dragonwing IQ-9075 EVK yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
instance segmentation
Only Qualcomm Dragonwing IQ-9075 EVK has published instance segmentation results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Qualcomm Dragonwing IQ-9075 EVK | 568 FPS inference_time · b=1 | yolov8_seg / YOLOv8-Segmentation w8a8 · Qualcomm AI Hub tflite (QAIRT 2.50.0.260828221209) · unknown | D | unknown power n/a no power published | Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published) |
AMD Ryzen AI Max+ (Strix Halo) iGPU:
No published instance segmentation results for AMD Ryzen AI Max+ (Strix Halo) iGPU or Qualcomm Dragonwing IQ-9075 EVK yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
pose estimation
Only Qualcomm Dragonwing IQ-9075 EVK has published pose estimation results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Qualcomm Dragonwing IQ-9075 EVK | 864 FPS inference_time · b=1 | hrnet_pose w8a8 · Qualcomm AI Hub tflite (QAIRT 2.50.0.260828221209) · mid-size CNN | D | unknown power n/a no power published | Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published) |
AMD Ryzen AI Max+ (Strix Halo) iGPU:
No published pose estimation results for AMD Ryzen AI Max+ (Strix Halo) iGPU or Qualcomm Dragonwing IQ-9075 EVK yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
image classification
Only Qualcomm Dragonwing IQ-9075 EVK has published image classification results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Qualcomm Dragonwing IQ-9075 EVK | 1965 FPS inference_time · b=1 | mobilenet_v2 w8a8 · Qualcomm AI Hub qnn_dlc (QAIRT 2.50.0.260828221209) · mobile-class CNN | D | unknown power n/a no power published | Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published) |
AMD Ryzen AI Max+ (Strix Halo) iGPU:
No published image classification results for AMD Ryzen AI Max+ (Strix Halo) iGPU or Qualcomm Dragonwing IQ-9075 EVK yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
semantic segmentation
Only Qualcomm Dragonwing IQ-9075 EVK has published semantic segmentation results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Qualcomm Dragonwing IQ-9075 EVK | 270 FPS inference_time · b=1 | deeplabv3_plus_mobilenet w8a8 · Qualcomm AI Hub onnx (QAIRT 2.50.0.260828221209) · mobile-class CNN | D | unknown power n/a no power published | Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published) |
AMD Ryzen AI Max+ (Strix Halo) iGPU:
No published semantic segmentation results for AMD Ryzen AI Max+ (Strix Halo) iGPU or Qualcomm Dragonwing IQ-9075 EVK yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
speech-to-text
Only Qualcomm Dragonwing IQ-9075 EVK has published speech-to-text results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Qualcomm Dragonwing IQ-9075 EVK | 196 FPS inference_time · b=1 | whisper_base / decoder float · Qualcomm AI Hub qnn_context_binary (QAIRT 2.50.0.260828221209) · Whisper base | D | unknown power n/a no power published | Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published) |
AMD Ryzen AI Max+ (Strix Halo) iGPU:
No published speech-to-text results for AMD Ryzen AI Max+ (Strix Halo) iGPU or Qualcomm Dragonwing IQ-9075 EVK yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
LLM generation
Only AMD Ryzen AI Max+ (Strix Halo) iGPU has published LLM generation results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| AMD Ryzen AI Max+ (Strix Halo) iGPU | 54.38 tok/s tg128 · b=1 | Llama 2 7B Q4_0 · llama.cpp Vulkan (FA on, commit fb4b273) · LLM 5–14B | C | 120 W spec platform spec envelope (not measured with this result) | llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) 2026-10-10 (page last edited) |
Qualcomm Dragonwing IQ-9075 EVK:
No published LLM generation results for Qualcomm Dragonwing IQ-9075 EVK or AMD Ryzen AI Max+ (Strix Halo) iGPU yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
How to read these numbers
Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.