83.79% of 2025 revenue linked to Tencent
As of 2026-09-11Reuters · Enflame’s Shanghai listing (source)TechInsights · Enflame S60 compute-chiplet analysis (source)Company dossier · Reviewed 2026-11-11
Enflame 燧原科技
AI accelerators and systems with Tencent as an anchor customer.
What the evidence says
TechInsights found TSMC N6 in the examined S60 compute chiplet; this does not identify the provenance of every later product. Enflame displayed an ESL64-O supernode with an orthogonal, cable-free electrical interconnect and optical scale-out, but supplied no card count, operating deployment, workload, reliability, power or matched performance result.
Enflame via PRNewswire; TechNode republication · Enflame CIIF release: ESL64-O and ZTE collaboration (source)Reuters · Enflame’s Shanghai listing (source)Enflame / CNINFO · Enflame 2026 third-quarter report (unaudited) (source)TechInsights · Enflame S60 compute-chiplet analysis (source)Enflame via ijiwei · Enflame Tencent conference release: inference software and long-context claims (source)China Star Market · On the ground at the 2026 Guoxin Expo as semiconductor companies display new products (source)Critical facts
The unaudited September 30 balance sheet reports RMB 7.709 billion of prepayments, versus RMB 388.132 million at year-end, and RMB 6.385 billion of contract liabilities, versus RMB 346.042 million. Nine-month operating cash outflow was RMB 2.017 billion, attributed to increased raw-material supplier payments. Q3 revenue was RMB 1.212 billion and the attributable net loss RMB 121.639 million. These financial balances do not identify suppliers, reserved wafer or HBM quantities, chip deliveries or a replenishable domestic supply route.
As of 2026-09-30Enflame / CNINFO · Enflame 2026 third-quarter report (unaudited) (source)In its October 29 conference release, Enflame describes operator fusion, memory optimization, scheduling, hierarchical KV Cache and prefill/decode separation, claiming stable high-throughput inference at million-token context lengths. It supplies no model, precision, accelerator count, latency, throughput, power or reproducible test configuration. This is a vendor capability claim, not a verified operating benchmark.
As of 2026-10-29Enflame via ijiwei · Enflame Tencent conference release: inference software and long-context claims (source)Enflame's October 16 release, republished October 18, identifies the model as ESL64-O (letter O) and names ZTE as co-developer. Its claim of supporting clusters above 10,000 cards describes design capability, not a measured or accepted deployment. See the appended correction to the earlier exhibition record.
As of 2026-10-16Enflame via PRNewswire; TechNode republication · Enflame CIIF release: ESL64-O and ZTE collaboration (source)Enflame displayed an ESL64-O supernode using its own AI accelerators, an OEX orthogonal electrical interconnect, a cable-free internal design and optical scale-out. The exhibition report did not establish an operating deployment, card count, topology, workload performance, utilization, reliability or power.
As of 2026-10-12China Star Market · On the ground at the 2026 Guoxin Expo as semiconductor companies display new products (source)Reuters reports IPO proceeds are intended mainly for fifth- and sixth-generation AI chips, software and large computing systems; funding plans are not delivered products.
As of 2026-09-11Reuters · Enflame’s Shanghai listing (source)TSMC N6, identified by independent teardown
As of 2026-02-03TechInsights · Enflame S60 compute-chiplet analysis (source)Company news
Timeline →Enflame filing documents larger prepayments and cash needs
Backfilled unaudited quarterly financial evidence from the original company filing.
Why it matters. Prepayments and contract liabilities are not completed chip shipments or proof of secured HBM supply.
Enflame / CNINFO · Enflame 2026 third-quarter report (unaudited) (source)Enflame describes long-context inference software at Tencent conference
Enflame reports hierarchical KV Cache and prefill/decode separation supporting million-token inference contexts, without numerical service metrics or test configuration.
Why it matters. The software mechanisms add specificity to its inference strategy, but neither matched performance nor deployment scale is independently established. The republished company release is not independent corroboration.
Enflame via ijiwei · Enflame Tencent conference release: inference software and long-context claims (source)Correction: Enflame supernode is ESL64-O, with letter O
The company release identifies ESL64-O, correcting the numeral-zero spelling in the earlier exhibition record, and names ZTE as co-developer.
Why it matters. The original event remains preserved. The naming correction and partner attribution do not establish operational cluster size, production provenance or workload performance.
Enflame via PRNewswire; TechNode republication · Enflame CIIF release: ESL64-O and ZTE collaboration (source)Enflame displays its ESL64-0 supernode
Enflame displayed an ESL64-0 supernode using its own AI accelerators, an OEX orthogonal electrical interconnect, a cable-free internal design and optical links intended for scale-out.
Why it matters. The disclosure adds system-level integration evidence but not deployment or performance evidence. The report supplied no card count, named customer, operating cluster, workload result, utilization, reliability, power or matched foreign-hardware comparison.
China Star Market · On the ground at the 2026 Guoxin Expo as semiconductor companies display new products (source)Enflame enters Shanghai’s public market
The accelerator company completed an approximately $912 million IPO.
Why it matters. Watch whether additional capital translates into broader customer adoption.
Reuters · Enflame’s Shanghai listing (source)Teardown identifies Enflame S60 manufacturing route
TechInsights identifies a TSMC N6 compute chiplet.
Why it matters. Chinese design does not alone establish domestic fabrication.
TechInsights · Enflame S60 compute-chiplet analysis (source)