MiaAI-Lab
Mia's AI Lab Joined Apr 2021 2,441 followers View on GitHub
- Stars
- 9,829
- across 109 public repos
- Rank
- #3,281
- of 323,846 users, top 2%
- Down 43 places this week
Repositories with 50+ stars
| Rank | Repository | Language | Stars |
|---|---|---|---|
| 45,222 | DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks | Python | 1,514 |
| 77,053 | sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard | JavaScript | 850 |
| 86,157 | GLM-5.3 Flash EXL3 for 2-4x DGX Sparks | Python | 755 |
| 101,670 | Qwen3.8-Flash-Next on ONE DGX Spark (TP=1) | Python | 630 |
| 105,680 | Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux | Python | 604 |
| 119,289 | GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold | Python | 529 |
| 129,754 | Qwen3.8 27B on SGLang for DGX Spark | Shell | 481 |
| 136,584 | DeepSeek-V4.1-Flash-1017 EXL3 on 2x DGX Sparks with TensorFold | Python | 454 |
| 147,164 | Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark | HTML | 417 |
| 155,165 | Qwen3.8 Flash Next on one DGX Spark (TensorFold) | Python | 393 |
| 171,877 | DeepSeek v4 Flash EXL3 on one DGX Spark | Python | 350 |
| 201,035 | DeepSeek-V4.1-Flash on 3-4x NVIDIA DGX Sparks | Python | 292 |
| 207,750 | DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks | Python | 281 |
| 243,317 | Deployment kit: Qwen3.8-27B EXL3 3.5bpw target + DFlash2 EXL3 5.0bpw speculative draft — launcher, config, model cards | Python | 233 |
| 455,866 | Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache | Shell | 108 |
| 465,939 | Cap the GPU clock on NVIDIA DGX Sparks across all your machines, persistently | Shell | 105 |
| 469,582 | 100 self-contained HTML pages made with Claude Opus 5.5 — gallery with screenshots and the exact prompts | HTML | 104 |
| 480,761 | GLM-5.3-Flash on DGX Sparks (ver 1104) with TensorFold | Shell | 101 |
| 484,538 | Qwen3.8 27B for DGX Spark / RTX 6000 PRO | Shell | 100 |
| 484,538 | Qwen3.8-27B-NVFP4 on a Single RTX 5090 (vLLM) | Shell | 100 |
| 516,717 | 2x DGX Spark recipe for LibertAIDAI/GLM-5.3-Flash-NVFP4 (NVFP4, Ray TP=2, multimodal) | Shell | 92 |
| 566,050 | GLM-5.3 EXL3 on DGX Sparks with TensorFold | Python | 82 |
| 571,592 | vLLM 0.25.1 serving stack for poolside/Laguna-S-2.1-NVFP4 with DFlash speculative decoding — DGX Spark & RTX 6000 PRO | Shell | 81 |
| 626,819 | GLM-5.2 NVFP4+AQLM on 3× DGX Spark — 380k context MTP serve stack | Shell | 72 |
| 633,649 | vLLM deployment for Unsloth Qwen3.6-35B-A3B-NVFP4-Fast on NVIDIA DGX Spark | Python | 71 |
| 640,697 | DeepSeek-V4.1-Flash-1017 on 4 DGX Sparks with TensorFold, switchless support | Shell | 70 |
| 713,786 | Qwen3.8-27B on SGLang for NVIDIA RTX PRO 6000 (96GB, SM120): DSpark speculative decoding, full 256K context, 8 concurrent requests | Python | 61 |
| 723,122 | Production-ready vLLM deployment wrapper for Qwen3.6-27B (NVFP4) — self-hosted OpenAI-compatible inference | Jinja | 60 |
| 797,198 | Qwen3.8-Flash-Next on two DGX Sparks with TensorFold | Shell | 53 |
Among 323,846 users
6.3k–10k stars: 2,566 users, including MiaAI-Lab
Stars along the bottom, and users in each band on a log scale
Where the stars are
Languages
- Python 6.2k stars, 64% · 14 repos
- Shell 1.4k stars, 14% · 11 repos
- JavaScript 850 stars, 9% · 1 repo
- HTML 521 stars, 5% · 2 repos
- Jinja 60 stars, 1% · 1 repo
When they were made
29 repos with 50+ stars, made in 2026
Quick stats
- Next rank
- +5 stars to reach #3,280
- Next milestone
- +100 stars to reach the top 1%
- Public repos
- 109, 29 with 50+ stars
- Popular repos
- 20 over 100 stars, 1 over 1k stars
- Top repo
- DeepSeek-v4-Flash-DSpark-2x-DGX-Spark, #45,222 of all repos, 15% of stars
- Smaller repos
- 786 stars from repos under 50