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 …

Sorry, not sure what results you are referring to ? TPS or ? What is “SCORE” ?

[image] JW2026: What is “SCORE” ? tool-eval-bench result (Tool-Call Benchmark), half of the posts in this topic has this bench results.

[image] pontostroy: tool-eval-bench result (Tool-Call Benchmark), half of the posts in this topic has this bench results. Just trying to figure where the “faster” came from.

[image] JW2026: “faster” faster in PP and TG if we compare cuda and vulkan llama.cpp backends

Same, I’m testing a few other combos today, but this ones does it for me. FP8, fast and MTP enabled. Briefly tried Qwen3.6-27B this morning and it’s painfully slow. Not sure if there’s an FP8 available, if there is, I’ll try it tonight. But I think I will stick with 3.6-35B-A3B-FP8 until a Quantize…

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?

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

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

VCR April 22, 2026, 8:10pm 139

FP8 has been available since 27B has launched. Qwen/Qwen3.6-27B-FP8 · Hugging Face

Topic		Replies	Views
Qwen3.6-27B is out! DGX Spark / GB10 agentic-ai	284	24295	June 3, 2026
Fastest Qwen 3.5 122B Int4 recipe on DGX Spark tested and published on Spark-Arena DGX Spark / GB10 llama	59	2439	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	417	19654	June 9, 2026
Qwen/Qwen3.5-122B-A10B - Alibaba/Qwen thought about us... :-D DGX Spark / GB10	340	16521	March 24, 2026
Does Qwen3.5-35B-A3B on GB10 leave a lot of performance on the table? DGX Spark / GB10 agentic-ai	40	5850	March 16, 2026
Qwen3.5 27B optimisation thread starting at 30+ t/s TP=1 DGX Spark / GB10 llama , agentic-ai	23	2695	May 11, 2026
Qwen3.5-122B-A10B NVFP4 Quantized for DGX Spark — 234GB → 75GB, Runs on 128GB DGX Spark / GB10 Projects	44	10954	April 9, 2026
Qwen3.5-397B-A17B + DGX Spark (duo) DGX Spark / GB10 Projects	59	5726	June 2, 2026
HOW-TO: Run Qwen3-Coder-Next on Spark DGX Spark / GB10 llama	92	9937	March 24, 2026
Bfloat16 Quality = Speed? DGX Spark / GB10	106	5312	May 26, 2026

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

Related topics