Tag
Explore by tags
Capability-targeted compression of Qwen3.8-Flash-Next: half the experts are removed and remaining weights quantized to 3.5 bpw, producing a 58.4 GB GGUF (29.6 GB resident) that preserves coding and multimodal ability while trading off other domains.
Adaptive-granularity post-retrieval evidence compressor for multimodal RAG that selects variable-sized regions from retrieved text, tables, images, and videos to retain necessary context while cutting irrelevant content. Key features include a hierarchy-based node encoder with parent-relative refinement and a critic that issues targeted follow-up retrievals; yields higher QA accuracy across five benchmarks and reduces reader-input tokens by ~14–28%.
Runs a pruned, NVFP4-quantized GLM-5.3-Flash variant tuned for Blackwell GPUs: 224 routed experts per layer and ~141 GiB of weights. Retains the multimodal vision tower, activates 18B params/token, supports vLLM and optional MTP speculative decoding; fits 2× DGX Spark or a ≥180 GB B200.