@WescheNex1q: 16 people chatting with Qwen3.6-35B at once ONE DGX Spark. This is a real capture, not a mockup: every token you see re…
Summary
A real-time demo shows 16 concurrent users chatting with Qwen3.6-35B on a single DGX Spark, achieving peak 440 tok/s total and 105 tok/s per user using NVFP4 + MTP-3 on vLLM.
View Cached Full Text
Cached at: 07/09/26, 09:52 PM
16 people chatting with Qwen3.6-35B at once
ONE DGX Spark.
This is a real capture, not a mockup: every token you see replays at its actual measured arrival time. Peaks ~440 tok/s total. A single user gets 105 tok/s. NVFP4 + MTP-3 on vLLM. https://t.co/lwmYWrvYAP
Similar Articles
Today I hit 181 toks/s (aggregate) on Qwen3.8-Flash-Next on 2x DGX Sparks
Achieved 181 tokens per second aggregate throughput on the Qwen3.8-Flash-Next model using a 2x DGX Spark cluster with optimizations like NVMe mapping and speculative decoding.
@Oluwaphilemon1: Qwen3.8-27B went from 82 to 381 tokens/sec on a single RTX 3090 with 24GB VRAM. Same GPU. Same model. Nearly 4.6× the r…
A developer boosted Qwen3.8-27B throughput from 82 to 381 tokens/sec on a single RTX 3090 using MTP, DFlash2 speculative decoding, context lookup, and prefix caching — no hardware upgrade needed. Ordinary chat performance still sits around 133 tokens/sec, highlighting that peak numbers come from reuse-heavy workloads.
@onusoz: 16x parallel Gemma-4-26B-A4B-NVFP4 runs 18 output tokens/s, aggregate 300 tok/s 1 DGX Spark with 128 GB unified memo…
@onusoz demonstrates running 16 parallel instances of NVIDIA's quantized Gemma-4-26B-A4B-NVFP4 model on a single DGX Spark with 128GB unified memory, achieving 300 tok/s aggregate, showcasing high concurrency without flashinfer.
40+tok/s - optimized recipe for Qwen 3.5 122B Int4 on a single DGX Spark with vLLM
User shares an optimized recipe for running Qwen 3.5 122B Int4 on a single DGX Spark with vLLM, achieving over 40 tokens per second. They invite others to try and further optimize it.
@rohanpaul_ai: Qwen 3.6 27B on a MacBook Pro M5 Max 64GB hitting 34tokens per sec, locally with atomic[.]chat 90% acceptance rate, i.e…
Qwen 3.6 27B achieves 34 tokens/sec on a MacBook Pro M5 Max 64GB locally with 90% draft acceptance, enabled by TurboQuant, GGUF, and llama.cpp, showcasing a major advancement in laptop-based AI inference.