igneum-network/igneum
1
0
Fork 0
Code Issues Pull requests Releases Activity

Bench table: the RTX 5080 row states the team's clock-lock pass as the card's figure (71.4 MH/s stock, 71.2 tuned at 146.6 W at a 1,100 MHz core lock, +83 W unlocked and +41 W at the best points for class v4, Hive core 1100) with the rented-fleet sampler reading and its 110 W gap kept in the note as the open question; /miners rebuilt

Browse source 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
igneum-labs 2026-10-08 02:13:09 +00:00
parent 9711cbf6e0
commit 1bc1752d90
2 changed files with 20 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
site/miner-bench.json
View file

@ -227,7 +227,7 @@
{
"card": "Apple M5 Max (40 GPU cores, Metal)",
"generator": "v2",
"mh_s": 27.0,
"mh_s": 27,
"watts": 21,
"mh_per_w": 1.29,
"miner": "igneum-miner Metal worker, class v3 program",
@ -250,7 +250,7 @@
{
"card": "Intel Arc B580 (12 GB)",
"generator": "v2",
"mh_s": 11.0,
"mh_s": 11,
"watts": null,
"mh_per_w": null,
"miner": "igneum-worker-opencl bench, class v4 program",
@ -294,24 +294,27 @@
{
"card": "NVIDIA RTX 5080 (16 GB)",
"generator": "v2",
"mh_s": 71.16,
"watts": 143.4,
"mh_per_w": 0.496,
"miner": "hive package 0.3.20 igneum-worker-cuda, class v4 program",
"date": "2026-10-07",
"source": "bench log: 7 October 2026, every rentable card on the hash (the fleet's sweep on rented cards; hive package 0.3.20, Ubuntu 24.04)",
"by": "measured by the fleet",
"note": "148.6 W maximum; the team's own 5080 on a dock reads 60 MH/s warming and gets its full Ember Tune on 7 October",
"v4_cost": "not measured (class v4 program only)",
"tuned": "stock, bench only (rented, not tuned)",
"driver_os": "NVIDIA driver 580.65.06, Ubuntu 24.04",
"mh_s": 71.2,
"watts": 146.6,
"mh_per_w": 0.486,
"miner": "the runner's card switch, class v4 program (job run-ca3-pc1-v4-eff-5080-20261007-d)",
"date": "2026-10-08",
"source": "bench log: 7 to 8 October 2026, the class v4 efficiency passes: the core clock lock on the RTX 5090 and the RTX 5080",
"by": "measured by the team",
"note": "the knee sits between 1,000 and 900 MHz (the rate within 0.3 percent of unlocked down to 1,000 MHz, 5.2 percent off at 900 on class v4); the draw floors from 1,500 MHz down. The rented fleet's 5080 read 71.16 MH/s at 143.4 W stock (hive package 0.3.20, Ubuntu 24.04, 7 October 2026), 110 W under this card's stock draw: the method differs per row (nvidia-smi on Linux, the runner's card switch on Windows) and neither is taken as the card's figure until the fleet re-measures",
"v4_cost": "83.4 W unlocked and 41 W at the best points for 0.2 percent of rate (class v4 71.41 MH/s at 253.1 W against class v3 71.28 at 169.7 W unlocked; measured 8 October 2026)",
"tuned": "core lock 1,100 MHz (the efficiency pass's best point: 71.20 MH/s at 146.6 W, 0.486 MH/W, 106.5 W recovered for 0.29 percent of rate), memory 14,801 MHz, the driver's power limit untouched",
"driver_os": "NVIDIA driver 617.14, Windows 11",
"hive": {
"core_mhz": null,
"core_mhz": 1100,
"mem_mhz": null,
"pl_w": null,
"label": "stock (no measured tune point; the 5080 and 9070 XT passes and the class v4 efficiency pass land theirs when read)"
"label": "core lock 1,100 MHz, memory stock, power limit untouched (measured 8 October 2026, the efficiency pass)"
},
"group": "buy"
"group": "buy",
"mh_s_display": "71.4 stock (71.2 tuned)",
"watts_display": "146.6 tuned (253 stock)",
"v4_short": "+83 W unlocked, +41 W at the best points"
},
{
"card": "NVIDIA RTX 3070 Ti (8 GB)",

2
site/miners.html
View file

File diff suppressed because one or more lines are too long