Qwen3.5-122B-A10B on a DGX Spark with DFlash speculative decode. One-shot Docker/vLLM installer. 80+ tok/s!
☆59Jun 29, 2026Updated 3 months ago
Alternatives and similar repositories for qwen3.5-122B-A10B-on-spark
Users that are interested in qwen3.5-122B-A10B-on-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:
- ☆17Jun 27, 2026Updated 3 months ago
- Headless / multi-user serving-mode for the DGX Spark: free unified memory for vLLM by paring back the desktop. Companion to qwen3.5-122B-…☆19Jun 29, 2026Updated 3 months ago
- Qwen3.5-122B-A10B on DGX Spark: 28.3 → 51 tok/s (+80%)☆315Aug 23, 2026Updated 2 months ago
- This is an experimental fork of Salvatore Sanfilippo's `antirez/ds4` project: ```text https://github.com/antirez/ds4 ``` This checkout …☆28Sep 23, 2026Updated 3 weeks ago
- DGX Spark inference dashboard — vLLM, SGLang, llama.cpp, WebGPU & sparkrun with agent-powered Auto-Fix and speed optimization☆67Oct 1, 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 4bpw + DFlash2) on 2x NVIDIA DGX Spark: one-shot installer, 33-74 tok/s c1, 1.3M+ context, vision☆43Sep 2, 2026Updated last month
- Fan Shroud for the Spark platform, for improved cooling performance on long workloads. Full STL/STEP files + electronics schematics☆39Sep 22, 2026Updated last month
- Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpar…☆410Aug 27, 2026Updated last month
- A plugin for Hermes to connect Hy-Memory as a memory provider as well as a dashboard view☆29Updated this week
- bf16 LoRA fine-tuning of [Qwen3.5-35B-A3B](https://huggingface.co/unsloth/Qwen3.5-35B-A3B) (a 35B-total / 3B-active Mixture-of-Experts vi…☆18Mar 12, 2026Updated 7 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…☆146Oct 6, 2026Updated 2 weeks ago
- Custom inference recipes for NVIDIA DGX Spark — Qwen 122B DFlash hybrid☆89Updated this week
- Some benchmark results of small models and quants that fit on DGX Spark☆51Aug 23, 2026Updated last month
- Web UI for sparkrun — launch and monitor inference workloads on NVIDIA DGX Spark☆28Jun 16, 2026Updated 4 months 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.
- Qwen3.6-35B-A3B-heretic NVFP4 + DFlash speculative decoding on DGX Spark (GB10/sm_121a). Source-built vLLM image + 7 patches + comprehens…☆146Oct 6, 2026Updated 2 weeks ago
- 4-5x faster Qwen3.5 on ASUS GX10 / DGX Spark — Hybrid INT4+FP8 + MTP via one shell script☆32Apr 16, 2026Updated 6 months ago
- Mixed-precision quantization for LLMs. Every layer refracts into a different format based on its sensitivity. Native compressed-tensors e…☆104Updated this week
- Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.i…☆483Oct 6, 2026Updated 2 weeks ago
- A dedicated effort to make an optimized, bleeding edge vLLM image using Docker to support DGX comprehensively☆128Feb 22, 2026Updated 8 months ago
- Profile repo — categorized index of NVFP4 model releases, DGX Spark inference stacks, Apple Silicon MLX builds, the voice-AI stack, and t…☆41Oct 6, 2026Updated 2 weeks 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
- FlashQLA TileLang GDN kernels ported to NVIDIA Blackwell consumer (GB10 / DGX Spark)☆18Jun 5, 2026Updated 4 months ago
- ☆17Aug 13, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- recipe for running Qwen3.8-Flash-Next on a single DGX Spark☆466Updated this week
- 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
- Official Spark Arena Recipe Registry☆66Oct 15, 2026Updated last week
- Qwen3.8-27B on one DGX Spark: SGLang + DFlash2 recipe, engine image, benchmarks, data and charts. By @redp314☆37Sep 6, 2026Updated last month
- Pure Rust Inference Engine☆712Updated this week
- Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, a…☆394Updated this week
- Docker configuration for running VLLM on dual DGX Sparks☆2,441Updated this week
- sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Live support: https://discord.com/invite/GH5kRg…☆547Updated this week
- Give text-only LLMs vision. A tiny OpenAI-compatible proxy that lets reasoning models (DeepSeek, Qwen, GLM…) see images by querying a sep…☆49Jul 7, 2026Updated 3 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆88Updated this week
- Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker…☆164Updated this week
- 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
- This repo contains the critical chat_template.jinja fix for Qwen3/3.5/3.6 to work smoothly in agentic task.☆97May 2, 2026Updated 5 months ago
- Recover usable memory on DGX Spark with a 64 KiB kernel: an opt-in NVIDIA UVM page-table packing patch, build tools, and measured validat…☆33Updated this week
- GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.☆90Updated this week
- Give the DeepSeek Harness (dsh) eyes with any text model + any vision model: a vision proxy for chat image attachments and an analyze_ima…☆12Sep 28, 2026Updated 3 weeks ago