{ "model_name": "edge0-145b-q3k", "display_name": "Edge0-145B", "family": "Edge0", "base_model": "Qwen3.8-Flash-Next", "architecture": "latent sparse MoE", "params": "145B", "active_params": "6.6 B", "layers": 48, "experts": 512, "experts_per_token": "10 routed + 1 shared", "latent_dim": 1792, "context": 262144, "build": "Q3_K", "weights": "40.81 GiB", "pack_format": "strata pack index v3", "exe": "strata", "args": [ "--pack", ".", "--native", "./model-skeleton.gguf", "--native-dense-gguf", "./model-skeleton.gguf", "--ple-gguf", "./ple-fp8.gguf", "--ple-io", "direct", "--expert-profile", "./profile.bin", "--expert-cache", "auto", "--prefill", "auto", "--pcie-frac", "0.1", "--spec", "4", "--spec-min-p", "0.5", "--mtp", "./mtp", "--max-context", "131072", "--kv", "int8", "--kv-resident", "32768", "--vram-reserve-mib", "700", "--pool-workers", "24", "--pcie-mode", "dma" ], "cwd": ".", "tokenizer": "./tokenizer", "log": "./serve.log", "port": 8123, "gpu": 0, "gpus_asked": true, "env": { "STRATA_LATENT_DENSE": "./latent_dense_q8.bin", "STRATA_LATENT_DENSE_FMT": "8", "STRATA_LATENT_A": "./experts.bin", "STRATA_LATENT_LABELS": "./labels.bin", "STRATA_EMBED_VRAM": "1", "STRATA_LATENT_FUSED": "1", "STRATA_LATENT_FUSED_DU": "1", "STRATA_LATENT_U_GPU": "1", "STRATA_LAT_FUSED_Q3K": "1" } }