Serving Qwen3.8-27B-FP8 on a single DGX Spark (GB10): 7.88 to 58.5 tok/s single-stream from decode strategy alone, weights untouched. Speculative decoding and prefix caching benchmarked, plus DFlash 2 — the only Qwen3.8-27B build that can serve it under vLLM.
☆55Sep 29, 2026Updated last month
Alternatives and similar repositories for Qwen3.8-27B-FP8-on-a-single-DGX-Spark
Users that are interested in Qwen3.8-27B-FP8-on-a-single-DGX-Spark are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Serving 4-bit Qwen3.8-27B on a single DGX Spark (GB10): 75 tok/s single-stream, 246 tok/s aggregate at 8-way concurrency. NVFP4 vs MixedI…☆51Sep 29, 2026Updated last month
- Qwen3.8-27B on one DGX Spark GB10: DFlash 2 for 65 tok/s C1 and 120 C4; EAGLE 3/1/4 for ~191 C8, ~330 C16 and ~535 C32; native 262K, pinn…☆13Oct 6, 2026Updated last month
- Reproducible Qwen3.8-27B NVFP4 + DFlash2 recipe and qualification evidence for one NVIDIA DGX Spark☆30Aug 21, 2026Updated 2 months ago
- ☆13Aug 27, 2026Updated 2 months ago
- Run Qwen3.8-Flash-Next (180B) on a single DGX Spark by keeping its 51B n-gram embedding table on NVMe☆125Aug 30, 2026Updated 2 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- GLM 5.3 Flash for 2x RTX 6000, Full Mixed EXL3 Support, Code C1 >220tps☆22Oct 25, 2026Updated 2 weeks ago
- 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 2 weeks ago
- GLM-5.2 QuantTrio TP=4+DCP2 on 4x NVIDIA DGX Spark (GB10) — tuned and measured under a real agent workload. Adaptive MTP, the indexer law…☆20Aug 24, 2026Updated 2 months ago
- Model-agnostic LLM benchmarking + tuning in one command. A model is a 15-key profile file. Built in production on a 4x NVIDIA DGX Spark c…☆10Sep 16, 2026Updated last month
- Serve LibertAIDAI/GLM-5.3-Flash-NVFP4 on 2x NVIDIA DGX Spark (GB10) with patched vLLM TP=2, 262k context, MTP-4.☆21Updated this week
- Index / recipe book for every GLM-5.3 (and GLM-5.2 foundation) serving recipe on NVIDIA DGX Spark (GB10): Flash + big 743B, TP2 + TP4, ev…☆13Aug 29, 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…☆74Updated this week
- 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
- Reproducible Docker deployment for Qwen3.8-27B NVFP4 on NVIDIA DGX Spark (GB10, SM121) via OpenAI-compatible vLLM. Known-good baseline + …☆12Aug 14, 2026Updated 2 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- 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
- Qwen3.8-27B NVFP4 (W4A16 shipped recipe) + MTP on NVIDIA DGX Spark GB10/SM121 — vLLM v0.27.2rc0, FP8 KV, 262K context, full reproducibili…☆27Aug 20, 2026Updated 2 months ago
- English guide + one-command patcher for the vLLM spin-wait bug that overheats NVIDIA DGX Spark / GB10. Credit: nacyot. CPU cores spin at …☆24Aug 17, 2026Updated 2 months ago
- llama-server start/stop scripts for Qwen3.6-35B-A3B UD-Q8_K_XL GGUF on DGX Spark☆26Jul 6, 2026Updated 4 months ago
- Exact SGLang runtime for GLM-5.3-Flash-NVFP4 on 4x RTX PRO 6000 Blackwell (SM120): flashinfer_cutlass MoE, DSA+KDA attention, NEXTN MTP5,…☆17Aug 27, 2026Updated 2 months ago
- First Int4-Int8Mix quantization of the full GLM-5.3 (743B), served on 4x NVIDIA DGX Spark (GB10) at TP4. Quantizer, verification gates, a…☆20Oct 6, 2026Updated last month
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆496Sep 10, 2026Updated last month
- Qwen3.8 27B on SGLang for DGX Spark☆481Sep 12, 2026Updated last month
- vLLM deployment for Unsloth Qwen3.6-35B-A3B-NVFP4-Fast on NVIDIA DGX Spark☆71Jul 29, 2026Updated 3 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- MiniMax-H3 33B audio+video DiT accelerated 1.54x on a single NVIDIA DGX Spark (GB10, sm_121): NVIDIA Sol-Engine FirstBlockCache + batched…☆34Aug 17, 2026Updated 2 months ago
- DeepSeek-V4-Flash-DSpark optimized vLLM 0.26.0 SM121 dual-GB10 evidence (NVFP4 KV, B12X, DSpark K6)☆31Aug 3, 2026Updated 3 months ago
- DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks☆1,512Oct 4, 2026Updated last month
- Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, option…☆48Oct 13, 2026Updated 3 weeks ago
- Verified Qwen3.8 Flash-Next GGUF recipe for one NVIDIA DGX Spark or ASUS Ascent GX10☆60Oct 20, 2026Updated 2 weeks ago
- DGX Spark (GB10/sm_121) port: DeepSeek-V4-Flash 159B on one Spark, GLM-5.2 753B across two. Prepacked 2-bit planes + unified-memory fixes…☆19Jul 20, 2026Updated 3 months ago
- SGLang 0.5.21 for Qwen3.8-Flash-Next on one RTX PRO 6000: 264.5 tok/s decode, W4A16 routed experts (KLD 0.0111 vs BF16), 262K context, ex…☆18Oct 26, 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
- AEON vLLM Ultimate — vLLM 0.27.1 built from source for DGX Spark / Blackwell (sm_121a/GB10). DSpark quantized Markov heads, DFlash SWA on…☆149Oct 6, 2026Updated last month
- 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.
- NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 + DSpark for DGX Spark, RTX 5090/6000 PRO (SGLang)☆24Aug 11, 2026Updated 2 months ago
- Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark☆412Sep 29, 2026Updated last month
- MiMo-V2.5 NVFP4 4-bit weights + NVFP4 4-bit KV cache + DFlash speculative decoding on 2× NVIDIA DGX Spark — 1M context, 3.4M-token KV poo…☆18Jul 13, 2026Updated 3 months ago
- qwen38-flash-next recipe for tp=2 GB10☆133Oct 29, 2026Updated last week
- Run DeepSeek-V4-Flash at full 1M context AND two MiniMax H3 video instances on the same two DGX Sparks. Benchmarked C1-C6.☆35Aug 7, 2026Updated 3 months ago
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆627Oct 4, 2026Updated last month
- Custom inference recipes for NVIDIA DGX Spark — Qwen 122B DFlash hybrid☆92Updated this week