schema = "m64/capsule@1" description = "Qwen3.8-Flash-Next IQ3_S on Strata (GB10). A local OpenAI-compatible chat endpoint for Qwen3.8-Flash-Next (Qwen's 125B-A6B MoE, ISTA-DASLab's GSQ-RCO IQ3_S GGUF) on Strata 0.2.13's DGX Spark engine, 64K context, with the MTP draft layer. Reads images, streams, tool calls. Needs no network." kinds = ["chat"] authors = ["dh7"] license = "mit" [hardware] platform = "linux-aarch64" gpu = "NVIDIA GB10" gpu_count = 1 # Unified memory: the experts are read in place from shard 1 (55 GB), the n-gram table (shard 2, 29 GB) is # locked in RAM, plus the pack, the draft layer, the vision tower and a 64K int8 KV cache. Measured on # gx10: ~63 GB in use at peak over a 5-hour agent benchmark (MemAvailable never below 49 GB). vram_gb = 72 driver = ">=580.65" disk_gb = 90 [runtime] sandbox = "container" # No image: the Dockerfile builds Strata 0.2.13's linux-aarch64 packages on ubuntu:24.04, pinned by digest. gpu = true shm_gb = 2 internal_port = 9000 health = "/health" expected_load_seconds = 900 model_name = "qwen3.8-flash-next-iq3_s-strata" user = "65534:65534" # ISTA-DASLab's GSQ-RCO shards at the revision Strata 0.2.13 pins (setup.py HF_REVISIONS), and the # picture reader (mounted; pictures are off in this capsule). [[artifacts]] type = "hf" repo = "ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF" revision = "ed59f92082b1e93c0e96d60a8b11aab089b52f09" include = ["README.md", "IQ3_S/*.gguf", "mmproj-Qwen3.8-Flash-Next-BF16.gguf"] mount = "/weights/qwen38fn"