Dontopedia

RTX 3060

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

RTX 3060 has 32 facts recorded in Dontopedia across 12 references, with 1 live disagreement.

32 facts·26 predicates·12 sources·1 in dispute

Mostly:rdf:type(5), is gpu hardware(1), is video card(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (17)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

includesGpuIncludes Gpu(2)

comparesCompares(1)

executedOnHardwareExecuted on Hardware(1)

expectedToOutperformExpected to Outperform(1)

hasPerformanceGapToHas Performance Gap to(1)

hasSubjectHas Subject(1)

involvesHardwareInvolves Hardware(1)

involvesSwapFromInvolves Swap From(1)

isHardwareUnfriendlyOnIs Hardware Unfriendly on(1)

measuredOnHardwareMeasured on Hardware(1)

notesTinyGridsFasterNotes Tiny Grids Faster(1)

runnableOnHardwareRunnable on Hardware(1)

runsOnHardwareRuns on Hardware(1)

shouldBeCompetitiveWithShould Be Competitive With(1)

superiorToSuperior to(1)

targetHardwareTarget Hardware(1)

Other facts (30)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

30 facts
PredicateValueRef
Rdf:typeHardware[8]
Rdf:typeHardware[9]
Rdf:typeHardware[10]
Rdf:typeGpu[11]
Rdf:typeHardware[12]
Is Gpu HardwareNVIDIA 3060[1]
Is Video Cardnull[2]
Has Cuda Coresover 3k[2]
Has Vram12G[2]
Supports Cu Blas Callsnull[2]
Achieves Points Per Second2.36B[3]
Performance MatchesMetal M4[3]
Is Gputrue[4]
Achieves Gpu Win Threshold1024[4]
Bandwidth Bound at High Ptsnull[4]
Evaluated on GridsPoint Based Grids[4]
Faster on Tiny Grids1d 2d Configs[4]
Faster Than Cpu Above1024[4]
Has Bandwidth Limitationnull[4]
Has Vram Capacity Gb12[4]
Performance Drops to Approx80[4]
Requires Threshold For3d Win4096[4]
Superior For1d2dnull[4]
Runs Python at~3K tok/s[5]
Achieves Tok Per S18700[6]
Used in Bakeoffnull[7]
Has Vram Capacity12[11]
Vram Capacity UnitGB[11]
Has Throughput At4m Points80[11]
Has Performance BottleneckVram Bandwidth Limitation[11]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

isGpuHardwareblah/posers/part-1
NVIDIA 3060
isVideoCardblah/vidya/part-10
null
hasCudaCoresblah/vidya/part-10
over 3k
hasVRAMblah/vidya/part-10
12G
supportsCuBLASCallsblah/vidya/part-10
null
achievesPointsPerSecondblah/watt-activation/part-547
2.36B
performanceMatchesblah/watt-activation/part-547
ex:metal-m4
isGpublah/watt-activation/part-568
true
achievesGpuWinThresholdblah/watt-activation/part-568
1024
bandwidthBoundAtHighPtsblah/watt-activation/part-568
null
evaluatedOnGridsblah/watt-activation/part-568
ex:point-based-grids
fasterOnTinyGridsblah/watt-activation/part-568
ex:1d-2d-configs
fasterThanCpuAboveblah/watt-activation/part-568
1024
hasBandwidthLimitationblah/watt-activation/part-568
null
hasVramCapacityGbblah/watt-activation/part-568
12
performanceDropsToApproxblah/watt-activation/part-568
80
requiresThresholdFor3dWinblah/watt-activation/part-568
4096
superiorFor1d2dblah/watt-activation/part-568
null
runsPythonAtblah/watt-activation/part-631
~3K tok/s
achievesTokPerSblah/watt-activation/part-641
18700
usedInBakeoffblah/watt-activation/part-648
null
typeblah/models/17
ex:Hardware
typeblah/vidya/10
ex:Hardware
typeblah/watt-activation/544
ex:Hardware
typeblah/watt-activation/565
ex:GPU
labelblah/watt-activation/565
RTX 3060
hasVramCapacityblah/watt-activation/565
12
vramCapacityUnitblah/watt-activation/565
GB
hasThroughputAt4mPointsblah/watt-activation/565
80
hasPerformanceBottleneckblah/watt-activation/565
ex:vram-bandwidth-limitation
typeblah/watt-activation/638
ex:Hardware
labelblah/watt-activation/638
RTX 3060

References (12)

12 references
  1. [1]Part 11 fact
    ctx:discord/blah/posers/part-1
  2. [2]Part 104 facts
    ctx:discord/blah/vidya/part-10
  3. [3]Part 5472 facts
    ctx:discord/blah/watt-activation/part-547
  4. [4]Part 56811 facts
    ctx:discord/blah/watt-activation/part-568
  5. [5]Part 6311 fact
    ctx:discord/blah/watt-activation/part-631
  6. [6]Part 6411 fact
    ctx:discord/blah/watt-activation/part-641
  7. [7]Part 6481 fact
    ctx:discord/blah/watt-activation/part-648
  8. [8]171 fact
    ctx:discord/blah/models/17
    • full textmodels-17
      text/plain2 KBdoc:agent/models-17/3891df99-201a-4926-bad2-89fe752c2f92
      Show excerpt
      [2026-04-23 19:16] ajaxdavis: lol might do this (files: Screenshot_from_2026-04-24_05-14-30.png) [2026-04-23 19:16] ajaxdavis: generate echo location heatmaps, seems doable [2026-04-24 08:50] lisamegawatts: 5.5 is growing on me: I’m going t
  9. [9]101 fact
    ctx:discord/blah/vidya/10
    • full textvidya-10
      text/plain3 KBdoc:agent/vidya-10/636e1043-0585-44b0-86c4-ecbe60c83f00
      Show excerpt
      [2026-03-20 11:25] foxhop.: awesome new video card with 12G & over 3k cuda cores! [2026-03-20 11:25] foxhop.: ? [2026-03-20 11:27] foxhop.: "We're building the disk." [2026-03-20 11:28] foxhop.: this screams GPT switch all "the" toward "a"
  10. [10]5441 fact
    ctx:discord/blah/watt-activation/544
    • full textwatt-activation-544
      text/plain2 KBdoc:agent/watt-activation-544/15208b8e-2c11-4018-9f0c-92c340329135
      Show excerpt
      [2026-03-23 05:47] xenonfun: ⏺ Server already killed by the test script timeout. The fundamental issue: round 1 works perfectly (all 10 workers got slices, computed on GPU, submitted, accepted). But the transition to round 2 isn't happe
  11. [11]5656 facts
    ctx:discord/blah/watt-activation/565
    • full textwatt-activation-565
      text/plain2 KBdoc:agent/watt-activation-565/bd81b9f3-fcaa-4cad-ba15-46cb0903d87c
      Show excerpt
      [2026-03-24 05:09] xenonfun: ``` ● Here's the full picture for your AMD 5900x + RTX 3060: Results ┌───────────┬────────────┬──────────────┬─────────────┬───────────────┐ │ Config │ Peak CPU │ Peak GPU │ GPU Speedup │ GPU Cr
  12. [12]6382 facts
    ctx:discord/blah/watt-activation/638
    • full textwatt-activation-638
      text/plain3 KBdoc:agent/watt-activation-638/539b1483-cc08-42f3-9ea1-6a7f6ae47ab8
      Show excerpt
      [2026-04-16 00:45] xenonfun: ``` ⏺ Let me answer the Python question first, then look at rayon parallelism. Python training setup (from scaling_wave_native_curriculum.py): - BATCH_SIZE = 32 (base script has BATCH_SIZE=16 with GRAD_ACCU

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.