Mixed-precision quantization for LLMs. Every layer refracts into a different format based on its sensitivity. Native compressed-tensors export, validated on Qwen3.6-35B-A3B MoE with MTP speculative decoding.
☆103Oct 9, 2026Updated this week
Alternatives and similar repositories for prismaquant
Users that are interested in prismaquant are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Live support: https://discord.com/invite/GH5kRg…☆537Updated this week
- Qwen3.5-122B-A10B on DGX Spark: 28.3 → 51 tok/s (+80%)☆315Aug 23, 2026Updated last month
- Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, a…☆380Updated this week
- Official Spark Arena Recipe Registry☆65Sep 3, 2026Updated last month
- Docker configuration for running VLLM on dual DGX Sparks☆2,372Updated this week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Web UI for sparkrun — launch and monitor inference workloads on NVIDIA DGX Spark☆28Jun 16, 2026Updated 3 months ago
- A dedicated effort to make an optimized, bleeding edge vLLM image using Docker to support DGX comprehensively☆126Feb 22, 2026Updated 7 months ago
- Some benchmark results of small models and quants that fit on DGX Spark☆51Aug 23, 2026Updated last month
- Linux hwmon driver for the NVIDIA DGX Spark (GB10 SoC) that exposes full system power telemetry via standard sensors / sysfs interfaces.☆34Mar 2, 2026Updated 7 months ago
- Real-time hardware and LLM inference monitoring — GPU, CPU, memory, and vLLM metrics streamed to a dashboard.☆131Updated this week
- 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
- DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding☆54Jun 28, 2026Updated 3 months ago
- Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker…☆160Updated this week
- A monitor of resources for DGX Spark☆25Feb 13, 2026Updated 7 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.
- Pure Rust Inference Engine☆705Updated this week
- ☆16Jun 27, 2026Updated 3 months ago
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆490Sep 10, 2026Updated last month
- Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.i…☆475Updated this week
- Scitrera builds of various CUDA containers for version consistency, starting primarily with NVIDIA DGX Spark Containers☆41Aug 21, 2026Updated last month
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆106Aug 20, 2026Updated last month
- ☆74Feb 27, 2026Updated 7 months ago
- Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models…☆53Updated this week
- ☆120Aug 6, 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.
- Qwen3.6-35B-A3B-heretic NVFP4 + DFlash speculative decoding on DGX Spark (GB10/sm_121a). Source-built vLLM image + 7 patches + comprehens…☆145Updated this week
- Operator-grade GPU monitor for NVIDIA GPUs with native GB10 / DGX Spark coherent UMA support — PSI pressure, clock detection, ConnectX-7 …☆34May 31, 2026Updated 4 months ago
- Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.☆272Updated 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 6 months ago
- A Prometheus metrics exporter for NVIDIA DGX Spark clusters.☆25Feb 16, 2026Updated 7 months ago
- Run Faster-Qwen3-TTS on NVIDIA DGX Spark GB10 (ARM64/SM121/CUDA13) - OpenAI-compatible TTS API with CUDA graph acceleration☆23Updated this week
- Run vLLM on 1-to-N NVIDIA DGX Spark servers (single Spark, 2 via direct cable, or 3+ via switched fabric) to serve or benchmark LLMs☆131Jun 22, 2026Updated 3 months ago
- A Home Assistant custom component used for generating a synthetic home☆20Updated this week
- An Enhanced TOP program to monitor your Nvidia DGX SPARK's Hardware☆38Jan 6, 2026Updated 9 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Compressed KV cache as cross-backend wire format for Metal + CUDA split inference over Thunderbolt 5☆15Apr 14, 2026Updated 5 months ago
- recipe for running Qwen3.8-Flash-Next on a single DGX Spark☆411Updated this week
- Complete guide to running Qwen3.5-35B-A3B on NVIDIA DGX Spark (GB10) with vLLM - installation, benchmarks, vision features, and troublesh…☆98Mar 11, 2026Updated 6 months ago
- AI-assisted development MCP providing long-term, on-device "AI memory" for IDEs. Powered by Kuzu GraphDB and exposed via MCP server☆14Jun 21, 2026Updated 3 months ago
- Collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices with Blackwell architecture.☆1,418Updated this week
- Universal Ethernet Direct Connect (UniEDC)☆31Apr 1, 2026Updated 6 months ago
- Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.☆85Updated this week