BrunoSanKI-PraxisApplied AI for decision-makers

GPU OBJECT :: source-gpu-geforce-rtx-5090

GeForce RTX 5090

Evidence-first hardware detail for local AI.

SOURCE_OBSERVEDSOURCE CANDIDATE
32GB
FAST MEMORY
28GB/s
BANDWIDTH
—PRICE
OBSERVATION
← All GPUsSpecsMarketVariantsModel fitPerformanceSoftwarePros / ConsCompareSources

DIRECT ANSWER

GeForce RTX 5090 provides 32 GB of fast memory, 28 GB/s of memory bandwidth, and reaches at least minimum memory fit for 7 of 9 currently listed BrunoSan models. Runtime/software compatibility for this source-observed object has not yet been promoted from an official vendor source. BrunoSan publishes tokens/s only with model- and runtime-specific benchmark evidence.

01 · HARDWARE

Technical data

Canonical GPU facts. Board-specific differences stay in variant evidence.

Fast memory / VRAM32 GBSOURCE_OBSERVED
Memory typeGDDR7SOURCE_OBSERVED
Memory bus512 bitSOURCE_OBSERVED
Memory bandwidth28 GB/sSOURCE_OBSERVED
Graphics processorGeForce RTX 5090SOURCE_OBSERVED
Processor familyNVIDIASOURCE_OBSERVED

02 · MARKET

Current market

Observed price

NO PRICE OBSERVATION

No promoted market-price observation is attached yet.

Buying guidance

Strong memory fit for Qwen3-Coder-30B-A3B, Qwen3-30B-A3B, Qwen3.5-35B-A3B and more. Verify runtime/driver support with the GPU vendor before purchase; software compatibility is not yet promoted BrunoSan truth.

03 · VARIANTS

Observed board variants

Dimensions, connectors and outputs stay variant-scoped.

VariantGTINPCIePSUPowerDimensionsDisplay
GIGABYTEGV-N5090GAMING OC-32GD4719331355791, 0889523048443PCI Express x16 5.01 000 W1x 16-pin342 × 70 × 152 mmDP 3 · HDMI 1
GIGABYTEGV-N5090AORUS M-32GD4719331355807, 0889523048450PCI Express x16 5.01 000 W1x 16-pin360 × 75 × 150 mmDP 3 · HDMI 1
GIGABYTEGV-N5090WF3OC-32GD4719331355838, 0889523048467PCI Express x16 5.01 000 W1x 16-pin342 × 65 × 150 mmDP 3 · HDMI 1
GIGABYTEGV-N5090AORUSX WB-32GD4719331355944, 0889523048672PCI Express x16 5.01 000 W1x 16-pin234 × 29 × 172 mmDP 3 · HDMI 1
GIGABYTEGV-N5090AORUSX W-32GD4719331355968, 0889523048696PCI Express x16 5.01 000 W1x 16-pin245 × 36 × 146 mmDP 3 · HDMI 1
GIGABYTEGV-N5090AORUSM ICE-32GD4719331355906, 0889523048597PCI Express x16 5.01 000 W1x 16-pin360 × 75 × 150 mmDP 3 · HDMI 1
MSIGEFORCE RTX 5090 32G VANGUARD SOC LAUNCH EDITION4711377302517PCI Express x16 5.01 000 W1x 16-pin357 × 76 × 151 mmDP 3 · HDMI 1
MSIGEFORCE RTX 5090 32G GAMING TRIO OC4711377302456PCI Express x16 5.0—1x 16-pin359 × 70 × 149 mmDP 3 · HDMI 1
ASUS90YV0LY1-M0NA004711387890349PCI Express 5.01 000 W1x 16-pin348 × 72 × 146 mmDP 3 · HDMI 2
ASUS90YV0LY0-M0NA004711387890325PCI Express 5.01 000 W1x 16-pin348 × 72 × 146 mmDP 3 · HDMI 2
ASUS90YV0LW0-M0NA004711387890288PCI Express 5.01 000 W1x 16-pin358 × 76 × 149 mmDP 3 · HDMI 2
ASUS90YV0LW1-M0NA004711387890301, 0197105890305PCI Express 5.01 000 W1x 16-pin358 × 76 × 149 mmDP 3 · HDMI 2
MSIGEFORCE RTX 5090 32G SUPRIM SOC4711377302487PCI Express x16 5.01 000 W1x 16-pin359 × 76 × 150 mmDP 3 · HDMI 1
MSIGEFORCE RTX 5090 32G SUPRIM LIQUID SOC4711377296380PCI Express x16 5.01 000 W1x 16-pin280 × 51 × 148 mmDP 3 · HDMI 1
ASUS90YV0LW2-M0NA004711387920817PCI Express 5.01 000 W1x 16-pin288 × 48 × 154 mmDP 3 · HDMI 2
MSIGEFORCE RTX 5090 32G VENTUS 3X OC4711377301633, 0824142402986PCI Express x16 5.01 000 W1x 16-pin325 × 67 × 139 mmDP 3 · HDMI 1
MSIGEFORCE RTX 5090 32G VANGUARD SOC0824142403143, 824142403143PCI Express 5.01 000 W1x 16-pin357 × 76 × 151 mmDP 3 · HDMI 1
ASUS90YV0LWB-M0NA004711636112109, 0199291112100PCI Express 5.01 000 W1x 16-pin358 × 76 × 149 mmDP 3 · HDMI 2
ASUS90YV0LWA-M0NA004711636112086, 0199291112087PCI Express 5.01 000 W1x 16-pin358 × 76 × 149 mmDP 3 · HDMI 2
GIGABYTEGV-N5090AORUSST ICE-32GD4719331356576PCI Express 5.01 000 W1x 16-pin360 × 75 × 150 mmDP 3 · HDMI 1
MSIGEFORCE RTX 5090 32G VENTUS 3X0824142402993, 824142402993PCI Express x16 5.01 000 W1x 16-pin325 × 67 × 139 mmDP 3 · HDMI 1
MSIGEFORCE RTX 5090 32G LIGHTNING Z—PCI Express x16 5.0—1x 16-pin260 × 61 × 151 mmDP 3 · HDMI 1
GIGABYTEGV-N5090AORUS IF-32GD4719331357337PCI Express x16 5.01 000 W1x 16-pin330 × 65 × 145 mmDP 3 · HDMI 1

04 · LOCAL AI FIT

Which BrunoSan models fit?

Exact BrunoSan model profiles, not generic 7B/14B buckets. Memory fit does not claim maximum context or runtime compatibility.

ModelMemory targetFitContext
GLM-4.7-Flash18–24 GBRecommended fitContext/KV cache unbenchmarked
Nemotron 3.5 Lightning 30B-A3B20–24 GBRecommended fitContext/KV cache unbenchmarked
Qwen3-30B-A3B20–24 GBRecommended fitContext/KV cache unbenchmarked
Qwen3-Coder-30B-A3B20–24 GBRecommended fitContext/KV cache unbenchmarked
Qwen3.5-35B-A3B20–24 GBRecommended fitContext/KV cache unbenchmarked
Qwen3.8-27B18–24 GBRecommended fitContext/KV cache unbenchmarked
gpt-oss-20b16–24 GBRecommended fitContext/KV cache unbenchmarked
Qwen3-Coder-Next 80B-A3B48–64 GBDoes not fit fast memoryContext/KV cache unbenchmarked
gpt-oss-120b64–96 GBDoes not fit fast memoryContext/KV cache unbenchmarked

05 · PERFORMANCE

Evidence before speed claims

Memory bandwidth: 28 GB/s

BENCHMARK TRUTH

No model/runtime-specific benchmark is registered. No tokens/s number is published.

06 · SOFTWARE

Runtime path

Runtime/software compatibility has not yet been promoted from an official vendor source. Hardware fit shown here is memory/spec evidence only.

UNKNOWN

OS: not yet promoted

07 · PROS

Strengths

  • 32 GB of fast memory
  • 28 GB/s evidenced memory bandwidth
  • Recommended-memory fit for 7 BrunoSan model profiles

08 · CONS

Limits

  • Fast memory is insufficient for 2 larger model profiles
  • No model/runtime-specific benchmark in the BrunoSan registry yet
  • Software/driver path not yet promoted as BrunoSan truth

09 · COMPARE

Nearby hardware choices

Related by memory capacity first; never a hidden performance ranking.

RTX 5000 Ada32 GB · 576 GB/s—Tesla M1032 GB · — GB/s—Arc Pro B65 32GB32 GB · 608 GB/s€1 234

10 · SOURCES

Provenance

Every displayed fact keeps its evidence scope. Curated SSOT wins over source observations; board-specific Icecat fields are not silently generalized to a GPU family.

Spec source →
Specs Icecat

Icecat source observations are provided AS IS and are not used for AI training by BrunoSan.

Icecat.biz → · AS IS disclaimer →

LOCAL AI FINDER

Put this GPU into your actual decision.

Model, budget, PSU, OS and software stack belong in the same decision.

Open Finder →