vLLM recipe: GLM-5.3-Flash EXL3 K2 on one DGX Spark GB10. Native MTP k=2. Measured tok/s.
☆26Sep 10, 2026Updated 2 months ago
Alternatives and similar repositories for GLM-5.3-Flash-EXL3-K2-DGX-Spark-recipe
Users that are interested in GLM-5.3-Flash-EXL3-K2-DGX-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:
- 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
- 1 spark glm 5.3 flash☆11Sep 7, 2026Updated 2 months ago
- Qwen3.8-27B on one DGX Spark: SGLang + DFlash2 recipe, engine image, benchmarks, data and charts. By @redp314☆37Sep 6, 2026Updated 2 months ago
- Pinned stock Qwen3.8-27B NVFP4 + DFlash2 recipe and measured evidence for one NVIDIA DGX Spark☆21Sep 10, 2026Updated 2 months ago
- Serve Qwen3.8-Flash-Next (turboderp ExLlamaV3 pack) on one NVIDIA DGX Spark with exllamav3☆64Oct 14, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 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
- ☆15Sep 5, 2026Updated 2 months ago
- Pinned, checksum-verified GLM-5.3-Flash EXL3 K2 recipe for one NVIDIA GB10.☆46Updated this week
- 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
- A native vLLM 0.26 DGX Spark recipe for Qwen3.6 35B-A3B NVFP4, focused on high aggregate throughput, 262K context, and production-friendl…☆15Aug 31, 2026Updated 2 months ago
- All-NVFP4 vLLM + DFlash2 K7 for Blackwell (SM120/SM121): NVFP4 target/draft/KV, 262K context, optional CPU vision sidecar.☆41Aug 28, 2026Updated 2 months ago
- Run frontier open-weight models privately on NVIDIA DGX Spark.☆15Oct 26, 2026Updated 2 weeks ago
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆629Oct 4, 2026Updated last month
- ☆55Sep 13, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- GLM-5.3-Flash (abliterated EXL3) on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8x faster decode than vLLM, 4x256k concurrent threa…☆122Oct 30, 2026Updated last week
- Qwen3.8 Flash Next on one DGX Spark (TensorFold)☆390Oct 30, 2026Updated last week
- Serve LibertAIDAI/GLM-5.3-Flash-NVFP4 on 2x NVIDIA DGX Spark (GB10) with patched vLLM TP=2, 262k context, MTP-4.☆21Nov 2, 2026Updated last week
- DeepSeek v4 Flash EXL3 on one DGX Spark☆350Aug 24, 2026Updated 2 months ago
- ☆15Sep 14, 2026Updated last month
- qwen38-flash-next recipe for solo GB10☆170Oct 30, 2026Updated last week
- DGX Spark EC fan speed override / rollback tool☆25Aug 23, 2026Updated 2 months ago
- DeepSeek-V4.1-Flash EXL3 vLLM recipe for 2x DGX Spark (GB10)☆28Sep 27, 2026Updated last month
- Local-first AI workbench for OCR, transcription, translation, image generation, mind maps and composable workflows. Built for DGX Spark.☆69Sep 2, 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.
- Qwen 3.8 Flash NVFP4 with PLE NVFP4 quantized to run on a single DGX Spark☆15Aug 28, 2026Updated 2 months ago
- 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…☆140Updated this week
- GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spe…☆65Updated 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
- Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quan…☆174Nov 2, 2026Updated last week
- 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
- GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.☆95Updated this week
- LLM engine with adaptive expert loading. DeepSeek V4.1 Flash (510 GB) on two DGX Sparks at its released MXFP4 weights.Or GLM 5.3 full EXL…☆33Nov 2, 2026Updated last week
- 8s of H3 video in 2m54s warm delivery on two DGX Sparks. Scene-specific LTX refinement, original-voice restoration, measured sync, clips …☆24Sep 12, 2026Updated last month
- 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 EXL3 for 2-4x DGX Sparks☆754Updated this week
- A 2MB sklearn classifier on consumer CPU beats Cohere's $10M+ 218B MoE on HumanEval☆13Oct 18, 2026Updated 3 weeks ago
- 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
- 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
- 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
- Fast, capable GLM-5.3-Flash FP4-Local on two DGX Sparks: opinionated Atlas serving and reproducible inference research.☆72Updated this week
- Capture, search, and rediscover every valuable moment on X (Twitter). 100% free, local-first browser extension.☆12Sep 26, 2026Updated last month
Are these results useful?