Hi everyone, I’m currently running Qwen3.5-35B-A3B FP8 on DGX Spark. It gives me a good quality/speed balance, but for my workloads — translation, French copywriting, and deep analysis of news articles — Qwen3.5-27B seems qualitatively stronger. The issue is that 27B FP8 is too slow/heavy for my b…

Did you try Qwen 3.5 122B Int4 Autoround? 50tok/s with 262k context window and Solid Quality for agentic tasks in my experience. Using it sucessfully in Opencode and Openwebui.

[image] sesmanovic: I’m currently running Qwen3.5-35B-A3B FP8 on DGX Spark. It gives me a good quality/speed balance, but for my workloads — translation, French copywriting, and deep analysis of news articles — Qwen3.5-27B seems qualitatively stronger. If we can trust the graphs on Qwen/Qwen3…

Definitely Qwen3.5 122B AutoRound, which is a 4bit quant by Intel on Hugging Face.

shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC is also worth a look - 4GB smaller than Intel’s [image] Qwen3.5-122B-A10B on single Spark: up to 51 tok/s (v2.1 — patches + quick-start + benchmark) DGX Spark / GB10 Qwen3.5-122B-A10B-int4-AutoRound-EC Extended Ca…

Interesting! How is your experience compare using both?

Hi folks, thanks for your replies. The issue on my side is that I can’t use a 122B model, because 80GB for a single model is just too much for my use case. I’m running 4 models at once, so I’m basically constrained to smaller MoE models. That said, I switched to Qwen3.6, and I’m currently testing Qw…

Have you considered Gemma 4 31B? Gives you the density you want with great assistant researcher capability for deep analysis and copy writing ?

There is also Autoround quant now: Intel/Qwen3.6-35B-A3B-int4-AutoRound · Hugging Face

If you want to stick to 27B, I’ve found this to work. It’s very fast for 27B. [image] GitHub - AEON-7/vllm-dflash: DFlash vLLM for DGX Spark — Plug & Play... DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

Best Q4 / NVFP4 model for quality Qwen3.5-27B or alternatives?

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

whpthomas April 16, 2026, 4:58pm 4

I wrote up my thoughts and reflections on this topic here Bfloat16 Quality = Speed

Topic		Replies	Views
Qwen3.8-27B on DGX Spark using vllm: NVFP4 vs FP8 performance DGX Spark / GB10 llm	8	5473	August 24, 2026
Qwen3-Next AWQ 4bit vs FP8 vs NVFP4 on single spark DGX Spark / GB10 jetson , llama , nemotron	7	3287	February 23, 2026
RedHatAI/Qwen3.5-122B-A10B-NVFP4 seems to be the best option for a single Spark DGX Spark / GB10 Projects llm	75	7658	May 4, 2026
Qwen3.5-122B-A10B NVFP4 Quantized for DGX Spark — 234GB → 75GB, Runs on 128GB DGX Spark / GB10 Projects	44	13603	April 9, 2026
PSA: State of FP4/NVFP4 Support for DGX Spark in VLLM DGX Spark / GB10	234	16372	May 15, 2026
Let's optimize nvidia/GLM-5.3-Flash-NVFP4 for 2× DGX Spark DGX Spark / GB10	184	10419	October 7, 2026
NVIDIA folks -- where is this promised nvfp4 speedup? DGX Spark / GB10	27	3348	March 26, 2026
The best 2x spark qwen 3.6 27b recipe DGX Spark / GB10	8	2262	July 6, 2026
From 20 to 35 TPS on Qwen3-Next-NVFP4 w/ FlashInfer 12.1f DGX Spark / GB10	10	2184	January 7, 2026
What's the best speed we can get with Qwen 3.6 27B without quantizing? DGX Spark / GB10	64	28029	July 6, 2026

Best Q4 / NVFP4 model for quality Qwen3.5-27B or alternatives?

Related topics