Tag
dgx-spark
Also taggednvfp4vllmdflashspeculative-decodingmixture-of-expertsabliterationdockeruncensored
Posts and projects tagged dgx-spark
- The AEON Forge catalog: every project and what to read first
A guided tour of the AEON Forge catalog: NVFP4 models for the DGX Spark, MLX builds for Apple Silicon, the voice stack, the media tools, the Orb and the Bench, with the article to read first in each group.
The Aeon Forge11 min read - Run your own AI benchmark: AEON Bench and the Bench Pod
AEON Bench measures any open model's quality and real speed on your own hardware, signs the result and ranks it with its exact recipe. Why a stranger's score can be trusted, how to read the boards, and the five steps to a first run.
The Aeon Forge14 min read - Qwen3-TTS server: streaming speech that starts in 0.4 seconds
An OpenAI-compatible Qwen3-TTS server for the DGX Spark that streams audio while the GPU is still generating: first audio in about 0.4 s, voice design and voice cloning loaded side by side, a voices library endpoint, and the version drift to check before you deploy.
The Aeon Forge8 min read - Qwen3-ASR server: transcription at 16 times real time on a DGX Spark
Qwen3-ASR on vLLM gives a DGX Spark a self-hosted, Whisper-compatible transcription endpoint for 30 languages and 22 Chinese dialects at about 16 times real time. Here is the pre-built image, the 0.6B and 1.7B variants, and the lessons from running it.
The Aeon Forge7 min read - Qwen 3.8 27B AEON Ultimate: the current flagship and how to serve it
Qwen3.8-27B AEON Ultimate Uncensored is the model I now serve on one Spark, two Sparks and the RTX box: what coherent abliteration removes and keeps, the NVFP4-MIXED weight lattice, the three seat recipes with their commands, and the rules that keep them running.
The Aeon Forge14 min read - Serving Qwen 3.6 35B-A3B heretic at NVFP4 with DFlash on a DGX Spark
How I serve an uncensored Qwen 3.6 35B-A3B at NVFP4 with DFlash speculative decoding on one DGX Spark: the seven container fixes, the mixture-of-experts angle, the drafter, the measured numbers and the exact command that works today.
The Aeon Forge11 min read - Ornith 1.0 35B AEON Ultimate keeps the coding and drops the refusals
I abliterated DeepReinforce's Ornith 1.0 35B, an agentic coding MoE, and kept the coder: 0 of 80 refusals, pass@1 identical to the base, a three-way BF16, NVFP4 and DFlash benchmark on a DGX Spark, and the quick start to serve it.
The Aeon Forge10 min read - Nemotron 3 Nano Omni AEON Ultimate, served uncensored on a DGX Spark
An abliterated Nemotron 3 Nano Omni that reasons over text, images and audio on one DGX Spark. How the twelve-dimension refusal removal was found, what NVFP4 costs against BF16, what the source-built vLLM image patches, and how to deploy it.
The Aeon Forge9 min read - modelopt-fast-moe cuts AWQ calibration time for MoE models at NVFP4
modelopt-fast-moe replaces the one-sample-at-a-time calibration loop that leaves a GPU mostly idle while nvidia-modelopt quantizes a Mixture-of-Experts model to NVFP4. What broke on a 26B MoE, what the batched loop fixes, and what it still leaves to you.
The Aeon Forge6 min read - Matrix VoIP agent: call your AI, and let it see through your camera
A headless Matrix VoIP agent that answers WebRTC calls from any Matrix client and talks back through local speech recognition, an LLM and streaming TTS, about 1.0 s to first speech on one DGX Spark, plus an optional camera look tool that keeps every frame in RAM.
The Aeon Forge9 min read - Magick Orb Docker: the headless Orb for any server
One docker run puts the headless Magick Orb on an x86 server, a Mac or a DGX Spark: Model Share over IPFS, the Agent Dashboard, MCP and REST, with no Raspberry Pi. What the container lacks versus the Pi, and why port 4001 matters.
The Aeon Forge6 min read - Gemma 4 31B DECKARD HERETIC at NVFP4 with DFlash on a DGX Spark
A dense, uncensored Gemma 4 31B with thinking, quantized to NVFP4 and served through a DFlash drafter on one DGX Spark. Single-stream decode went from 11 to 39 tokens per second, 32 concurrent requests reach 427, and reasoning and tool calling stay intact.
The Aeon Forge11 min read - Gemma 4 26B-A4B at NVFP4: a mixture-of-experts recipe for a DGX Spark
How I serve Gemma 4 26B-A4B, a mixture-of-experts model at NVFP4, on one DGX Spark with a DFlash drafter: the production recipe, the bench recipe behind 816 tok/s at c64, and the drafter defects that made my earlier numbers wrong.
The Aeon Forge10 min read - DeepSeek-V4 on two DGX Sparks: an experimental TP=2 image
An experimental vLLM image that serves DeepSeek-V4-Flash across two DGX Sparks at tensor parallel 2 over RoCE: the seven GB10 gaps it patches, why PIECEWISE graphs are the rule, what the numbers do and do not prove, and a two-node quick start.
The Aeon Forge7 min read - DDTree on vLLM: candid research notes on tree speculation for Qwen3.6
DDTree puts tree-shaped speculative decoding into vLLM for Qwen3.6 on a DGX Spark. These lab notes show what works, what breaks inside a hybrid attention model, the numbers so far, and why production should stay on DFlash.
The Aeon Forge8 min read - ComfyUI for the DGX Spark: the AEON media production base
A Docker build of ComfyUI for the DGX Spark with CUDA 13, SageAttention v3 for sm_121a and NVFP4 weights, pulling Flux 2, LTX 2.3 and ACE-Step on first start. What broke, what the flags mean, how local and remote modes work, and why three AEON media repos sit on it.
The Aeon Forge10 min read - AEON vLLM Ultimate: one serving image for the DGX Spark
AEON vLLM Ultimate is vLLM built from source for the DGX Spark's GB10 and shipped as one 18.3 GB image that serves the whole AEON fleet with speculative decoding and NVFP4 weights. Here is why it exists, what broke on the way, and how to pull and run it.
The Aeon Forge14 min read - AEON Bench recipe lab: tuning vLLM flags one at a time on a DGX Spark
The AEON Bench recipe lab treats a serve recipe as an experiment: change one flag, bench, read the curve. The knobs in order of effect, the speculative decoding trap behind 33 versus 517 tok/s on a DGX Spark, the 816 tok/s recipe to steal, and four traps that fake a result.
The Aeon Forge11 min read