DSV4.1-Flash-1017 SAGE EXL3 (1.62 bpw) on one DGX Spark with vLLM: DSpark MTP, cold-expert ATS alias, tile-K 16 MoE, memory guard, measured 31-34 tok/s
☆42Nov 4, 2026Updated last week
Alternatives and similar repositories for DSV4.1-Flash-1017-EXL3-Spark-recipe
Users that are interested in DSV4.1-Flash-1017-EXL3-Spark-recipe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Qwen3.8 Flash-Next (NVFP4) on NVIDIA Flare for one DGX Spark / ASUS GX10: greedy, 8-agent speculative decoding, mixed prefill☆17Updated this week
- Nemotron 3.5 Super VL (NVFP4) on one DGX Spark with TensorFold 1.0.12 and 18 lossless engine patches☆11Oct 24, 2026Updated 3 weeks ago
- Serve Qwen3.8-Flash-Next (turboderp ExLlamaV3 pack) on one NVIDIA DGX Spark with exllamav3☆65Oct 14, 2026Updated last month
- Run Qwen3.8-Flash-Next (main agent) and MiniCPM-V 4.7 (subagents) EXL3 together on one DGX Spark at full 262K context, with a tested Herm…☆10Oct 14, 2026Updated last month
- Pinned, checksum-verified GLM-5.3-Flash EXL3 K2 recipe for one NVIDIA GB10.☆46Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Serve DeepSeek-V4-Flash-Vision EXL3 MixedK (full 256 experts) on one NVIDIA DGX Spark with vLLM — recipe, loader patches, and receipts☆14Sep 7, 2026Updated 2 months ago
- Qwen3.8 Flash Next on one DGX Spark (TensorFold)☆408Oct 30, 2026Updated 2 weeks ago
- GLM-5.3-Flash EXL3 2.05 on one DGX Spark — TP1 vLLM, DFlash2 K5, concurrency, 262K context, and published fidelity measurements☆57Sep 22, 2026Updated last month
- Verified Qwen3.8 Flash-Next GGUF recipe for one NVIDIA DGX Spark or ASUS Ascent GX10☆60Updated this week
- 1 spark glm 5.3 flash☆11Sep 7, 2026Updated 2 months ago
- DeepSeek-V4.1-Flash on a single DGX Spark (GB10): resident hot experts + NVMe streaming, DSpark, OpenAI API. Work in progress.☆130Sep 16, 2026Updated 2 months ago
- NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 + DSpark for DGX Spark, RTX 5090/6000 PRO (SGLang)☆25Aug 11, 2026Updated 3 months ago
- ☆16Sep 25, 2026Updated last month
- qwen38-flash-next recipe for solo GB10☆175Oct 30, 2026Updated 2 weeks ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Did your change make your LLM server faster? Measure it: faster, slower, or too close to call. Linux and Apple Silicon.☆16Nov 3, 2026Updated last week
- GLM-5.3-Flash EXL3 K2 2.33bpw on ONE DGX Spark: native MTP (layer 45, 288 experts), CUDA graphs on, full 262,144 ctx. Measured ~19 tok/s …☆11Sep 19, 2026Updated last month
- 🚗 LIMCARS Local Inference Monitor · Cost Analyzer · Recipe Server☆13Updated this week
- Run the AEON Bench suite on your own hardware: verified HuggingFace pull → serve → benchmark (text · agentic ×3 harnesses · vision · audi…☆25Oct 6, 2026Updated last month
- DeepSeek v4 Flash EXL3 on one DGX Spark☆353Aug 24, 2026Updated 2 months ago
- Qwen3.8-27B NVFP4 on SGLang (DGX Spark / SM121): official image pin, native DSpark/EAGLE click-run, matched evals☆21Aug 19, 2026Updated 2 months ago
- An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine tha…☆80Updated this week
- Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpar…☆415Aug 27, 2026Updated 2 months ago
- Serve Ornith-1.5-35B-A3B (NVFP4 + in-checkpoint MTP, 256k ctx) on one DGX Spark — vLLM b12x recipe plus CUDA-graph fixes.☆33Aug 19, 2026Updated 2 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- ☆19Sep 9, 2026Updated 2 months ago
- Fast & opinionated local AI routing: one MCP server that loads local image and video models on demand on your own GPU box (DGX Spark firs…☆102Updated this week
- DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM ki…☆147Updated this week
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆640Oct 4, 2026Updated last month
- Capping GPU clocks on NVIDIA GB10: -12C peak temp, -36% GPU power, ~1.6% throughput cost. Measurement harness, raw data, and the systemd …☆80Jul 31, 2026Updated 3 months ago
- Measured SM121 compatibility recipe for MiniMax H3 FL2VA on one NVIDIA DGX Spark with vLLM-Omni and online FP8.☆66Oct 22, 2026Updated 3 weeks ago
- Uncensored DeepSeek-V4.1-Flash-1017 on 2x DGX Spark: refusals 94 to 6, same answers as DeepSeek's API, 2,008 tok/s prefill at 128K, 113 t…☆62Oct 27, 2026Updated 2 weeks ago
- BertholomusAI recipe: DeepSeek-V4.1-Flash-1017 on 2x NVIDIA DGX Spark (GB10), our own TensorFold TP2 engine. Weights: bertholomus EXL3 2.…☆71Nov 4, 2026Updated last week
- ☆811Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Agent Traffic Control☆50Updated this week
- DeepSeek-V4.1-Flash on 4x DGX Spark (GB10): exact 4-node TensorFold (Zig) recipe, vision, 1M context☆14Nov 4, 2026Updated last week
- Qwen3.8-Flash-Next (NVFP4) on DGX Spark in vLLM: one Spark 43.9 tok/s with our disk-backed n-gram table patch, staged gather and reduced-…☆137Sep 7, 2026Updated 2 months ago
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆887Updated this week
- A community-owned map of LLM inference engine configurations — benchmarks, evals and coverage gaps, hosted on GitHub Pages. The repo is t…☆16Oct 19, 2026Updated 3 weeks ago
- Cap the GPU clock on NVIDIA DGX Sparks across all your machines, persistently☆110Nov 9, 2026Updated last week
- Serve EXL3 (ExLlamaV3 trellis) quantized models on vLLM fork runtimes — any architecture, mixed per-layer bitrates, composable with sourc…☆27Nov 5, 2026Updated last week
Are these results useful?