|
Qwen3.5-122B-A10B on single Spark: up to 51 tok/s (v2.1 — patches + quick-start + benchmark)
|
|
314
|
8030
|
April 19, 2026
|
|
Collecting eval results for Spark-sized quants of models
|
|
11
|
326
|
April 19, 2026
|
|
Request to increase RPM limit for NIM API (Development)
|
|
4
|
156
|
April 17, 2026
|
|
AI Models That Run on Jetson Orin Nano Super (8GB) — A Practical Guide
|
|
4
|
1106
|
April 16, 2026
|
|
Request for Rate Limit Increase for NIM API
|
|
1
|
58
|
April 16, 2026
|
|
Weekend Home Lab: Qwen3.5 9B on Jetson Orin Nano Super with TurboQuant4 (100K token window)
|
|
4
|
192
|
April 15, 2026
|
|
My DGX Spark Hangs ... is this normal?
|
|
4
|
181
|
April 13, 2026
|
|
Can not run Qwen3-VL-8B-Instruct-FP8 on Jetson AGX Thor using vllm
|
|
7
|
79
|
April 13, 2026
|
|
Local-first coding agent that auto-configures llama.cpp for maximum hardware performance
|
|
0
|
147
|
April 13, 2026
|
|
RedHatAI/Qwen3.5-122B-A10B-NVFP4 seems to be the best option for a single Spark
|
|
74
|
4556
|
April 11, 2026
|
|
Unable to Accept Terms for Model llama-3.3-nemotron-super-49b-v1.5-1.14.0
|
|
1
|
30
|
April 8, 2026
|
|
No luck with Gemma 4 on Jetson Nano Super
|
|
8
|
710
|
April 8, 2026
|
|
Creating a 50 GB Swap File on Jetson AGX Orin (Root on NVMe)
|
|
2
|
43
|
April 7, 2026
|
|
Fast Large-file and LLM Downloads with aria2 on NVIDIA Jetson AGX Orin
|
|
1
|
41
|
April 7, 2026
|
|
Production-Ready Guide: TinyLlama Fine-Tuning on Jetson Orin Nano 8GB with Complete Solution
|
|
3
|
101
|
April 1, 2026
|
|
**Title:** NIM qwen3.5-35b-a3b:1.7.0-variant fails on Jetson AGX Thor — Triton ptxas-blackwell does not recognize sm_110a
|
|
4
|
113
|
April 1, 2026
|
|
Does NanoLLM support Jetpack 7.0?
|
|
1
|
35
|
March 31, 2026
|
|
Ollama Docker container problem
|
|
5
|
89
|
March 30, 2026
|
|
The MODULE_SHDN_N signal of T5000 module with our carrier board is pulled low, causing the device to shut down
|
|
10
|
100
|
March 30, 2026
|
|
Running NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 on the Nvidia Jetson Thor
|
|
9
|
695
|
March 30, 2026
|
|
Sglang:26.02-py3 requires installation of 3 python modules
|
|
4
|
78
|
April 11, 2026
|
|
Jetson Orin TensorRT-Edge-LLM not support QWen3.5-2B
|
|
2
|
111
|
March 25, 2026
|
|
GPU stats in Live VLM WebUI
|
|
7
|
58
|
April 6, 2026
|
|
[GB10] vLLM + DeepSeek-R1-32B on Blackwell aarch64 — 4 more failure modes (v2 protocol)
|
|
0
|
182
|
March 19, 2026
|
|
LLM not working getting error
|
|
3
|
46
|
March 18, 2026
|
|
R3840 在这个平台上部署大模型,如何能离线跑大模型呢
|
|
6
|
82
|
March 16, 2026
|
|
Seeking Best Practices for Deploying Efficient RAG Systems on NVIDIA Jetson Edge Devices
|
|
2
|
42
|
March 16, 2026
|
|
Recipes to run Qwen3.5 models on Thor
|
|
1
|
366
|
March 16, 2026
|
|
How to run vllm on jetpack 6.0
|
|
3
|
85
|
April 7, 2026
|
|
TRT LLM for Inference with NVFP4 safetensors slower than LM studio GGUF on the Spark
|
|
9
|
1170
|
March 6, 2026
|