GPU OBJECT :: source-gpu-geforce-rtx-4090

GeForce RTX 4090

Evidence-first hardware detail for local AI.

SOURCE_OBSERVEDSOURCE CANDIDATE
24GB
FAST MEMORY
21GB/s
BANDWIDTH
PRICE
OBSERVATION
← All GPUsSpecsMarketVariantsModel fitPerformanceSoftwarePros / ConsCompareSources

DIRECT ANSWER

GeForce RTX 4090 provides 24 GB of fast memory, 21 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 / VRAM24 GBSOURCE_OBSERVED
Memory typeGDDR6XSOURCE_OBSERVED
Memory bus384 bitSOURCE_OBSERVED
Memory bandwidth21 GB/sSOURCE_OBSERVED
InterfacePCI Express 4.0SOURCE_OBSERVED
Graphics processorGeForce RTX 4090SOURCE_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-N4090AORUS M-24GD4719331311483PCI Express 4.01 000 W1x 16-pin358 × 75 × 163 mmDP 3 · HDMI 1
MSIGEFORCE RTX 4090 GAMING X TRIO 24G4711377019217PCI Express 4.0850 W1x 16-pin337 × 77 × 140 mmDP 3 · HDMI 1
GIGABYTEGV-N4090AORUSX W-24GD4719331311490PCI Express 4.0850 W1x 16-pin238 × 40 × 141 mmDP 3 · HDMI 1
GIGABYTEGV-N4090AERO OC-24GD4719331312916, 0889523036624PCI Express 4.01 000 W1x 16-pin342 × 75 × 150 mmDP 3 · HDMI 1
GIGABYTEGV-N4090WF3V2-24GD4719331313524, 0889523038321PCI Express 4.0850 W1x 16-pin331 × 56 × 136 mmDP 3 · HDMI 1
MSIGEFORCE RTX 4090 GAMING X SLIM 24G4711377134361, 0824142336687PCI Express 4.0850 W1x 16-pin322 × 62 × 136 mmDP 3 · HDMI 1
MSIGEFORCE RTX 4090 VENTUS 3X E 24G OC4711377134958PCI Express 4.0850 W1x 16-pin322 × 62 × 136 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: 21 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

  • 24 GB of fast memory
  • 21 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.

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.

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 →