Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
codingagentic
User reports 60 t/s on a 2x DGX Spark cluster with a vLLM recipe.
The setup uses a 1M context window.
User praises NVFP4 support and performance improvements, and compares the cluster favorably to Strix and M5 for prompt processing.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
long-contextagenticcodingvision
User reports retrieval at 832K tokens with 3/3 success.
DFlash speculative decoding gives roughly 3x speedup.
RPC split is slower than single-node.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports DeepSeek-V4-Flash-0731 at 74.8 tok/s single-stream on real coding prompts on 2x DGX Spark.
Setup is vLLM 0.25.2 with tensor parallel 2 over RoCE, DSpark speculative decoding (spec7) and NVFP4 MLA KV cache, with KV capacity of 2.74M tokens.
The user puts the speculative speedup at 2.74x over a 27.3 tok/s bandwidth floor. Prefill runs at ~1.7-1.9k tok/s with a 42 s TTFT on a 64k prompt, a random-token benchmark gives 33.8 tok/s, and spec3 wins at 4 concurrent streams with 105.7 aggregate.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
User reports Ling-3.0-flash at 40.2 tok/s single stream decode with the Q5_K_M quant on one DGX Spark, from benchmarks posted by sudoingX on X.
Setup is the community GGUF quant ladder, with 5.1B active out of 124B parameters.
Q4_K_M reaches 38.2 tok/s and Q6_K 32.0 tok/s. DeepSeek V4 Flash measured 16.5 tok/s on the same box.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
User reports Ling-3.0-flash (124B) at 38.7 tok/s on the official INT4 quant on one DGX Spark, from benchmarks posted by sudoingX on X.
The community GGUF reaches 35.2 tok/s, and the result is 2.4x what DeepSeek V4 Flash does on the same machine. The benchmarker first posted that the official quants do not run on a single Spark, then corrected that two days later.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
User reports 51.06 t/s single-stream and 184.03 t/s aggregate at c6 on 2x DGX Spark in TP2.
Setup is SGLang with QSA, NEXTN and FlashInfer GDN.
Disabling NEXTN gives 26.4 t/s at c1 and 111.8 t/s at c6. Medium thinking scored 22/24 on a 24-task LiveBench-style pilot.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports 49.7 t/s decode on structured output and 34.8 t/s decode on prose with TP2 across two DGX Sparks, plus prefill of about 2,875 t/s for 11k tokens.
Setup is MTP k=3 in eager mode. MTP acceptance is about 3.8 tokens/step on structured output.
A single node reaches about 35 t/s on structured output.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
agenticlong-context
User reports Qwen3.8-Flash-Next at 30-50 tok/s single-stream decode on 2x NVIDIA DGX Spark linked by a direct ConnectX-7 cable.
Setup is vLLM with the RadixArk NVFP4 quant, TP=2 across both boxes, MTP speculative decoding with 3 tokens at about 40% acceptance, 512K context stretched from 262K with YaRN, and a 47.7 GiB n-gram embedding table mmap'd from NVMe instead of loaded into memory.
With about 9 concurrent agent sessions the engine reaches 181 tok/s aggregate, peaking at 195.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports MTP3 as the default and MTP4 as the peak.
Setup includes a bug fix for a draft parallel config missing a DCP copy.
Prefill reaches about 475 tps and decode at bs=3 reaches about 48 tps.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports the full Kimi K3 model running on a 16x DGX Spark cluster at an average of 20+ t/s, peaking at 38 t/s, with prefill at 750 t/s.
This is a first run, and the user plans to optimize and publish a vLLM image.
User is setting up a 16x DGX Spark cluster to run frontier models locally.
User mentions DeepSeek V4 pro, Kimi K3, GLM 5.5, and Minimax M4 as future models.
No benchmark numbers are provided.
User reports GLM-5.1-NVFP4 at 434 GB served across a 16x DGX Spark cluster with unified memory at TP=8.
User plans to test DeepSeek and Kimi on the same cluster.
User plans a future prefill/decode split using M5 Ultra Mac Studios.