Popular repositories Loading

1. GLM-5.3-Flash-EXL3-K2-DGX-Spark-recipe GLM-5.3-Flash-EXL3-K2-DGX-Spark-recipe Public

   vLLM recipe: GLM-5.3-Flash EXL3 K2 on one DGX Spark GB10. Native MTP k=2. Measured tok/s.

   Python 25 2

2. vllm-exl3 vllm-exl3 Public

   Serve EXL3 (ExLlamaV3 trellis) quantized models on vLLM fork runtimes — any architecture, mixed per-layer bitrates, composable with source-format non-routed weights

   Python 18 9

3. FreeToken FreeToken Public

   Forked from FlashML-org/FreeToken

   Python 16 1

4. hermes-agentic-bench hermes-agentic-bench Public

   Agentic test batteries for local models via Hermes Agent - scripted tools + real Hermes CLI sessions

   Python 14

5. DeepSeek-V4-Flash-Vision-EXL3-MixedK-DGX-Spark-recipe DeepSeek-V4-Flash-Vision-EXL3-MixedK-DGX-Spark-recipe Public

   Serve DeepSeek-V4-Flash-Vision EXL3 MixedK (full 256 experts) on one NVIDIA DGX Spark with vLLM — recipe, loader patches, and receipts

   Python 14 1

6. Qwen3.8-Flash-Next-EXL3-DGX-Spark-recipe Qwen3.8-Flash-Next-EXL3-DGX-Spark-recipe Public

   Serve Qwen3.8-Flash-Next (turboderp ExLlamaV3 pack) on one NVIDIA DGX Spark with vLLM + vllm-exl3

   Python 13 1