╭────────────────────────────────────────────────────────────────────────╮ │ │ │ R I G M A R K // AGENT WORKLOAD RECEIPT │ │ BENCHMARKS LOCAL AI HOW CODING AGENTS ACTUALLY USE IT │ │ ● 15/15 BASIC OUTPUT GATES PASSED │ │ │ ├─ MODEL ────────────────────────────────────────────────────────────────┤ │ │ │ beam-1.0 │ │ │ ├─ SINGLE STREAM ────────────────────────────────────────────────────────┤ │ │ │ WORKLOAD tok/s Range tok/s Last (s) Checks │ │ PROSE 37.1 29.8–45.7 80.2 ✓ 5/5 │ │ CODE 41.8 40.7–42.8 139.9 ✓ 5/5 │ │ STRUCTURED* 59.4 58.7–60.1 11.5 ✓ 5/5 │ │ │ │ * Predictable JSON ceiling; not general agent performance. │ │ Decode medians are estimates; rates include streamed reasoning. │ │ │ ├─ PREFILL ──────────────────────────────────────────────────────────────┤ │ │ │ DEPTH Cold tok/s Cold TTFT (s) Replay TTFT (s) │ │ 8K 1,478 5.54 3.20 │ │ 32K 1,441 22.74 3.43 │ │ 64K 1,366 47.99 3.76 │ │ Medians; replay is an immediate repeat, not a proven hit. │ │ │ ├─ CAPPED CONCURRENT GENERATION ─────────────────────────────────────────┤ │ │ │ Aggregate tok/s: C1 38.7 | C2 48.9 | C4 63.3 │ │ C4: 0/12 normal stops; 0/12 with visible output. │ │ Capped throughput includes reasoning; not completed agent tasks. │ │ │ ├─ APPLIANCE ────────────────────────────────────────────────────────────┤ │ │ │ Hardware: 2x NVIDIA DGX Spark (GB10, 128 GB unified memory each), │ │ ascent-03 + ascent-04 │ │ Topology: TP2, one rank per Spark, RoCE over ConnectX-7 │ │ Checkpoint: bertholomus/Beam-1.0-501B-A23B-EXL3-3bpw-2xGB10 @ local │ │ folder │ │ Quantisation: EXL3 3 bpw weights, BF16 activations │ │ KV cache: engine default for this lane │ │ Engine: TensorFold fork github.com/bertholomus/TensorFold branch │ │ beam-1.0-tp2 lineage │ │ │ ├─ SETTINGS ─────────────────────────────────────────────────────────────┤ │ │ │ SUITE: DEFAULT SETTINGS │ │ REQUEST: {} │ │ Temperature 0.0 | top_p 1.0 | seed 20260905 | protocol 1.3.0 │ │ Decode: 5 runs, 8192-token cap | Prefill: 8K/32K/64K, 3 pairs │ │ Concurrency: C1/C2/C4, 3 rounds, 256-token cap; workload code │ │ Cache isolation: random-salt-per-pair │ │ Comparison ID: 2026-10-two-sparks-four-models-v1 │ │ │ ├─ RECEIPT ──────────────────────────────────────────────────────────────┤ │ │ │ SOURCE git:946394fa53db • clean │ │ RIGMARK RELEASE: ahead of v0.0.4 (unreleased checkout) │ │ JSON sha256:142a174917c66aee… │ │ SHARE THE CARD • LINK THE JSON RECEIPT • #RIGMARK │ │ github.com/alexellis/rigmark │ │ │ ╰────────────────────────────────────────────────────────────────────────╯