"""Thousandfold cost model: energy and dollars per solved task vs B2026.
B2026 = DeepSeek-V4-Pro-class on GB300 NVL72, $0.12 per M output tokens at ~27 tok/s/user (InferenceX via Silicon Report),
energy per output token ~0.5-2 J (derived; Rubin measured ~10 J at 300 tok/s/user, B200 ~0.36 J on a 5B-active model)."""
S = { # low (pessimistic), central, high (optimistic)
'base_J_per_tok': (0.5, 1.0, 2.0),
'base_usd_per_Mtok': (0.12, 0.12, 0.12),
'core_active_B': (24, 12, 8), # wired ternary reasoning core, billions of weights
'pJ_per_weight_op': (0.3, 0.1, 0.03), # wired ternary + shared partial sums, incl. wiring
'act_sparsity_gain': (1.0, 2.0, 4.0), # event-driven: zero activations do not toggle fanout
'data_mJ_per_tok': (0.6, 0.2, 0.08), # recurrent state + sparse global attn + memory-tier lookups
'overhead_mult': (1.6, 1.3, 1.15), # leakage, I/O, control, sampling
'tok_ratio': (1.5, 0.67, 0.25), # new tokens per task / baseline tokens per task
'deep_share': (0.10, 0.05, 0.02), # tasks escalated to a 5x larger wired deep core
'deep_cost_ratio': (6, 5, 5),
'gpu_share': (0.01, 0.001, 0.0), # tasks that still fall back to B2026-class GPUs
'set_capex_usd': (40e3, 15e3, 8e3), # one core set: dies + package + HBM for state
'set_power_W': (600, 1000, 2000),
'utilization': (0.35, 0.5, 0.7),
'life_years': (3, 3, 3),
'usd_per_kWh': (0.10, 0.08, 0.06),
'pue': (1.4, 1.3, 1.2),
'nre_usd': (150e6, 40e6, 10e6), # per frozen-core generation (masks + design + verification)
'life_tokens': (1e16, 3e16, 1e17), # tokens served by one frozen core generation
'memtier_usd_per_Mtok':(2e-4, 5e-5, 2e-5),
}
def run(i):
p = {k: v[i] for k, v in S.items()}
core_mJ = p['core_active_B']*1e9 * p['pJ_per_weight_op']*1e-12 / p['act_sparsity_gain'] * 1e3
tok_mJ = (core_mJ + p['data_mJ_per_tok']) * p['overhead_mult']
# per-token cost of the tiered wired fleet (deep core priced as a multiple), then GPU fallback by share
wired_mix = (1 - p['deep_share']) + p['deep_share'] * p['deep_cost_ratio']
E_new_tok = tok_mJ * 1e-3 * wired_mix # J per token, wired tiers
thr = p['set_power_W'] / (tok_mJ * 1e-3) # tok/s per set at full power
capex = p['set_capex_usd'] / (p['life_years']*3.156e7 * thr * p['utilization']) * 1e6
energy_usd = tok_mJ*1e-3 * p['pue'] / 3.6e6 * p['usd_per_kWh'] * 1e6
nre = p['nre_usd'] / p['life_tokens'] * 1e6
usd_new_tok = (capex + energy_usd + p['memtier_usd_per_Mtok']) * wired_mix + nre
# per task: tokens ratio, then Amdahl blend with GPU fallback at baseline cost per task
E_task = (1-p['gpu_share']) * E_new_tok * p['tok_ratio'] + p['gpu_share'] * p['base_J_per_tok']
U_task = (1-p['gpu_share']) * usd_new_tok * p['tok_ratio'] + p['gpu_share'] * p['base_usd_per_Mtok']
return dict(core_mJ=core_mJ, tok_mJ=tok_mJ, tok_per_s_per_set=thr,
usd_per_Mtok=dict(capex=capex, energy=energy_usd, nre=nre, total=usd_new_tok),
energy_x_per_token=p['base_J_per_tok']/E_new_tok, usd_x_per_token=p['base_usd_per_Mtok']/usd_new_tok,
energy_x_per_task=p['base_J_per_tok']/E_task, usd_x_per_task=p['base_usd_per_Mtok']/U_task)
for i, name in enumerate(['low', 'central', 'high']):
r = run(i)
print(f"{name:8s} core {r['core_mJ']:.3f} mJ | token {r['tok_mJ']:.3f} mJ | {r['tok_per_s_per_set']:,.0f} tok/s/set | "
f"$/Mtok capex {r['usd_per_Mtok']['capex']:.5f} energy {r['usd_per_Mtok']['energy']:.6f} nre {r['usd_per_Mtok']['nre']:.5f} total {r['usd_per_Mtok']['total']:.5f}")
print(f" energy x/token {r['energy_x_per_token']:,.0f} x/task {r['energy_x_per_task']:,.0f} | dollars x/token {r['usd_x_per_token']:,.0f} x/task {r['usd_x_per_task']:,.0f}")
# Amdahl illustration: GPU fallback share caps the gain
print("Amdahl cap (energy x/task, central otherwise):")
for s in [0.0, 0.0005, 0.001, 0.01, 0.05]:
S['gpu_share'] = (S['gpu_share'][0], s, S['gpu_share'][2]); print(f" fallback {s:.2%}: {run(1)['energy_x_per_task']:,.0f}x energy, {run(1)['usd_x_per_task']:,.0f}x dollars")
print("With via-programmed fabric (NRE per model ~$3M central) and 0.05% GPU fallback:")
S['nre_usd'] = (20e6, 3e6, 1e6); S['gpu_share'] = (0.01, 0.0005, 0.0)
for i, name in enumerate(['low', 'central', 'high']):
r = run(i); u = r['usd_per_Mtok']
print(f" {name:8s} energy x/task {r['energy_x_per_task']:,.0f} | dollars x/task {r['usd_x_per_task']:,.0f} | $/Mtok capex {u['capex']:.5f} nre {u['nre']:.5f} total {u['total']:.5f}")