I run a single DGX Spark serving models headless with sparkrun into the OpenCode harness. I’d like to hear how others have set theirs up, especially on one node (so much of the recipe ecosystem assumes 2-Spark tensor-parallel): Which models you’ve found genuinely useful solo, and for what (autonom…

initially I wrote shi** but it blurred it, so I corrected to small :P

Returning to the OT.. albond/Qwen3.5-122B-A10B. Has been extremely good for me. Mainly running in Agent Zero. DeepSeek-V4-Flash (Q2 GGUF, llama.cpp) Also very hard worker.. Oddly, I just read about Holo-3.1-35B-A3B today, and it is on my list to try. Would be interested in your findings etc.. Qw…

Qwen3.6-35B-A3B-FP8 (vLLM) — daily for hermes, auto tasks, simple coding etc. Fallback to CC/CLI (Opus) on hard coding tasks.

I currently use at home and at work Qwen3.5-122B-A10B-int4-autoround with vLLM (eugr/spark-vllm-docker). Until one week ago also with dflash, but it currently is not working.

Need to try it later. I wrote the other recipe by myself, based on the existing one of qwen3.5-122b. I have problems with dflash also for other models (qwen3.6-35b) therefore i think that there is somewhere an error, but dont know where.

I have tried Qwen3.5-122B-a10b, but haven’t found it to be noticeably better than Holo 3.1-35B-a3b. It writes the maching bignum Pi calculator, but fails at the spigot version (Opus 4.8 typically does it single attempt, and deepseek flash after some debugging). As of now I’m looking for a smaller / …

I’ve managed to run shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC and other dflash models, after Claude Opus monkey-patched the vllm container for me cd ~/recipes mkdir -p patches cat > patches/patch_pr45207_mamba.py <<'PYEOF' #!/usr/bin/env python3 """vLLM PR #45207 backport — pad the Mamba…

From the Qwen3.6 27B thread it was stated that PrismaAURA is worse than PrismaSCOUT, I have not tested this for myself yet so ymmv. You can also see my message in that thread ( here ) for by far the fastest Qwen3.6 27B recipe with decent quality which I have personally tested on my spark, quite easy …

Single-Spark setups — which models do you actually run for coding, and how? (sharing mine + a test prompt)

Accelerated Computing DGX Spark / GB10 User Forum DGX Spark / GB10

entrpi June 25, 2026, 12:07pm 22

Does this work for you? DFlash for Qwen3.5-122B-A10B = 80+ tok/s on 1x Spark!

Topic		Replies	Views
Best model for single Spark? DGX Spark / GB10 spark , deepseek	53	4999	July 14, 2026
HOW-TO: Run Qwen3-Coder-Next on Spark DGX Spark / GB10 llama	92	10812	March 24, 2026
DFlash for Qwen3.5-122B-A10B = 80+ tok/s on 1x Spark! DGX Spark / GB10 Projects agentic-ai	66	6845	July 19, 2026
Vibe Coding with NVIDIA DGX Spark DGX Spark / GB10	39	5871	May 10, 2026
Qwen/Qwen3.6-35B-A3B (and FP8) has landed DGX Spark / GB10 agentic-ai	309	29765	June 22, 2026
Qwen3.6-27B is out! DGX Spark / GB10 agentic-ai	300	30585	June 30, 2026
Best 2026 model for agentic work on a 2-node Spark cluster? DGX Spark / GB10 agentic-ai , deepseek , openclaw	33	5443	July 1, 2026
Fastest Qwen 3.5 122B Int4 recipe on DGX Spark tested and published on Spark-Arena DGX Spark / GB10 llama	59	4026	June 3, 2026
Qwen/Qwen3.5-122B-A10B - Alibaba/Qwen thought about us... :-D DGX Spark / GB10	340	17544	March 24, 2026
Can someone please just help me set the DGX Spark up for optimal LLM use? DGX Spark / GB10 llama	11	1528	June 20, 2026

Single-Spark setups — which models do you actually run for coding, and how? (sharing mine + a test prompt)

Related topics