Minisforum MS-R1 (as tested by Jeff Geerling) vs NVIDIA Jetson AGX Thor

(independent test)independent test systemNo licensed photo yet

NVIDIAedge referenceNo licensed photo yet

NVIDIA Jetson AGX Thor is faster in all 3 like-for-like comparisons (largest gap: LLM generation, 19.48×).

	Minisforum MS-R1 (as tested by Jeff Geerling)	NVIDIA Jetson AGX Thor
Best LLM generation	71.36 tok/s C 2025-11-10 (page last edited)	523 tok/s C 2026-07-21 (page last edited)
Power	n/a	130 W Module TDP, Module, max of range 40-130 W
Perf / W	n/a	4.02 tok/s/W Module TDP, Module, max of range 40-130 W
Price	n/a	$5499 list
Workloads with data	1 of 7	2 of 7

Best published LLM generation result per platform (may be from different like-for-like groups — see data). n/a = not published; never estimated.

Show data — all workloads, sources and like-for-like groups

object detection

Only NVIDIA Jetson AGX Thor has published object detection results.

Platform	Result	Model · precision · stack	Grade	Power	Source
NVIDIA Jetson AGX Thor	719 FPS inference_time · b=1	YOLO26n FP16 · Ultralytics TensorRT · nano (YOLO-n)	B	130 W Module TDP, Module, max of range 40-130 W reported in result source — Module TDP, Module, max of range 40-130 W	Ultralytics documentation (benchmark table) 2026-10-13 (page last edited)

Minisforum MS-R1 (as tested by Jeff Geerling):

◌

No published object detection results for Minisforum MS-R1 (as tested by Jeff Geerling) or NVIDIA Jetson AGX Thor yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

instance segmentation

◌

No published instance segmentation results for Minisforum MS-R1 (as tested by Jeff Geerling) or NVIDIA Jetson AGX Thor yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

◌

No published pose estimation results for Minisforum MS-R1 (as tested by Jeff Geerling) or NVIDIA Jetson AGX Thor yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

image classification

◌

No published image classification results for Minisforum MS-R1 (as tested by Jeff Geerling) or NVIDIA Jetson AGX Thor yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

semantic segmentation

◌

No published semantic segmentation results for Minisforum MS-R1 (as tested by Jeff Geerling) or NVIDIA Jetson AGX Thor 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

◌

No published speech-to-text results for Minisforum MS-R1 (as tested by Jeff Geerling) or NVIDIA Jetson AGX Thor yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

LLM generation

✓ Like-for-like: model-size class LLM 5–14B, batch 1. Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
NVIDIA Jetson AGX Thor	41.32 tok/s tok/s gen, concurrency 1 · b=1	Deepseek R1 7B n/s on page · NVIDIA (vLLM/TensorRT-LLM per page) · LLM 5–14B	D	130 W Module TDP, Module, max of range 40-130 W reported in result source — Module TDP, Module, max of range 40-130 W	NVIDIA Jetson Benchmarks on or before 2025-11-08
Minisforum MS-R1 (as tested by Jeff Geerling)	34.52 tok/s generation_throughput · b=1	llama3.1:8b Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) · LLM 5–14B	C	unknown power not published not published	Jeff Geerling ai-benchmarks issue results (comments) 2025-11-10 (page last edited)

✓ Like-for-like: model-size class LLM >40B, batch 1. Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
NVIDIA Jetson AGX Thor	15.00 tok/s generation_throughput · b=1	Nemotron 3 Super 120B-A12B NVFP4 · vLLM · LLM >40B	C	130 W Module TDP, Module, max of range 40-130 W reported in result source — Module TDP, Module, max of range 40-130 W	NVIDIA Jetson AI Lab benchmarks (benchmarks.json) 2026-07-21 (page last edited)
Minisforum MS-R1 (as tested by Jeff Geerling) CPU-only	0.770 tok/s generation_throughput · b=1	Llama 3.1:70b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) · LLM >40B	C	38.20 W ● Measured, Whole system reported in result source — Measured, Whole system	Jeff Geerling ai-benchmarks README (Findings tables) 2026-09-22 (page last edited)

✓ Like-for-like: model-size class LLM ≤4B, batch 1. Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
NVIDIA Jetson AGX Thor	122 tok/s generation_throughput · b=1	Qwen3-VL-2B NVFP4 · vLLM · LLM ≤4B	C	130 W Module TDP, Module, max of range 40-130 W reported in result source — Module TDP, Module, max of range 40-130 W	NVIDIA Jetson AI Lab benchmarks (benchmarks.json) 2026-07-21 (page last edited)
Minisforum MS-R1 (as tested by Jeff Geerling)	71.36 tok/s generation_throughput · b=1	llama3.2:3b Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) · LLM ≤4B	C	unknown power not published not published	Jeff Geerling ai-benchmarks issue results (comments) 2025-11-10 (page last edited)

Grades: A audited MLPerf · B third-party · C community · D vendor. How we rank · JSON