And yet another candidate to be tested. Still struggling to get stable performance in terms of tool calling with Qwen3.5 (may be I just missed a fix) and/or Gemma4… and they pushed out already the next. 😅 [image] Qwen/Qwen3.6-35B-A3B-FP8 · Hugging Face We’re on a journey to advance and …

For the ones that like to go down the rabbit hole Extended Calibration (EC) INT4 AutoRound quantization of Qwen/Qwen3.6-35B-A3B , a 35B MoE (3B active, 128 experts) multimodal model. Drop-in replacement for Intel/Qwen3.6-35B-A3B-int4-AutoRound with wider calibration settings for improved quality on …

GPT got the Intel quant working with TP=2. A few notes: Have to patch in conch-triton-kernels. Did this with a separate dockerfile using a current TF5 image FROM vllm-tf5:20260423 RUN uv pip install -U conch-triton-kernels Obviously rename it docker build -t vllm-tf5:20260423-conch . Must se…

Hi, was having reboots and error during heavy loads with big context and token loads. came to below recipe, seems stable now build for latest firmware and patch level gx10 # Qwen/Qwen3.6-35B-A3B model in native FP8 format recipe_version: "1" name: Qwen35-35B-A3B # HuggingFace model to downl…

I was not able to run this successfully with TP=2 (dual node setup). Did you have a chance to try dual node by chance?

I am bit fried, lets see what comes out of it :) ● Root cause Marlin kernel needs output_size_per_partition % 64 == 0. Our A3B expert weights split across TP=2 give 32 — Marlin rejects. Suggested fixes: –quantization gptq or reduce TP. Two fallback paths worth trying: Pipeline parallel (PP=2) — s…

I tried this build and got some good results +56% throughput and +63% prefill on my best build. [image] GitHub - AEON-7/Qwen3.6-NVFP4-DFlash: Qwen3.6-35B-A3B-heretic NVFP4 + DFlash... Qwen3.6-35B-A3B-heretic NVFP4 + DFlash speculative decoding on DGX Spark (GB10/sm_121a). Source-built vL…

Hey, It really feels like things are moving quite fast these days, just when you begin to get stable results with one model, a newer version comes along. From what you’re experiencing with Qwen3.5 and Gemma 4, it doesn’t seem like anything is going wrong on your side. These models can still be a l…

[image] chibri: 3.6 35B recipe I’ll create the recipe, what is your GitHub username so I can credit you?

Intel/Qwen3.6-35B-A3B-int4-AutoRound is gone right?

Can you run this full test as well? (so we are all using same benchmarks to compare) Introducing Tool Eval Bench CLI - #16 by serapis ?

Qwen/Qwen3.6-35B-A3B (and FP8) has landed

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

Bilabong007 April 24, 2026, 6:31am 145

I tried this build and got some good results +56% throughput and +63% prefill on my best build.

Topic		Replies	Views
Qwen3.6-27B is out! DGX Spark / GB10 agentic-ai	300	33561	June 30, 2026
What's the best speed we can get with Qwen 3.6 27B without quantizing? DGX Spark / GB10	64	26521	July 6, 2026
Fastest Qwen 3.5 122B Int4 recipe on DGX Spark tested and published on Spark-Arena DGX Spark / GB10 llama	59	5109	June 3, 2026
Qwen3.5-122B-A10B on single Spark: up to 51 tok/s (v2.1 — patches + quick-start + benchmark) DGX Spark / GB10 cuda , performance , docker , performance-tuning , llm	434	27607	June 24, 2026
Qwen/Qwen3.5-122B-A10B - Alibaba/Qwen thought about us... :-D DGX Spark / GB10	340	18844	March 24, 2026
Does Qwen3.5-35B-A3B on GB10 leave a lot of performance on the table? DGX Spark / GB10 agentic-ai	40	7042	March 16, 2026
Qwen3.5 27B optimisation thread starting at 30+ t/s TP=1 DGX Spark / GB10 llama , agentic-ai	23	3340	May 11, 2026
New 2.5x Faster Qwen3.6 NVFP4 Unsloth quants DGX Spark / GB10	20	4378	July 13, 2026
Single-Spark setups — which models do you actually run for coding, and how? (sharing mine + a test prompt) DGX Spark / GB10 spark , llama , agentic-ai , deepseek , dgx	60	8335	August 19, 2026
Qwen3.8-27B on dual Sparks DGX Spark / GB10 agentic-ai	17	5264	August 22, 2026

Qwen/Qwen3.6-35B-A3B (and FP8) has landed

Related topics