Choose my GPU

Answer nine questions. We rank the GPUs in our catalog by fit for local AI on your stack — top picks, alternates, and what to avoid. Hand-written rationale per card, honest caveats, and a one-click handoff into the custom build engine.

We don’t fake tok/s numbers. Every recommendation cites a model class and a workload-realistic range. Cards over your budget appear last with explicit framing. Recommendations are rule-based scoring, not measured benchmarks.

Configure your build

Tell us about your build

URL updates as you change fields. Showing the balanced default — change any field to refine.

USD ceiling. We treat over-budget cards as 'avoid' unless they'd otherwise have been a top pick — those land in 'Worth saving up for'.

Hard cut for vendor compatibility. NVIDIA + macOS = avoid (CUDA dropped in 10.13). Apple Silicon + Windows = impossible. AMD + macOS = abandoned.

Sets the VRAM target. 'Coding' wants 24GB minimum, 'chat' is fine at 8GB. Different workloads have different sweet-spot VRAM tiers.

Beginners get steered toward NVIDIA + Apple — the only paths where Ollama / LM Studio 'just work' with no driver wrangling.

Maximum catalog power for one GPU. Cards above this limit are excluded from recommendations. Allow additional PSU capacity for the CPU, other components and transient loads.

Thermal headroom proxy. High-power cards in small cases get loud first. Apple Silicon scores high for 'silent' because it actually is.

Workstation cards (RTX A6000, H100) have weak gaming drivers. Apple Silicon doesn't game. Consumer Ada/Blackwell does both well.

Crude perf-per-watt proxy via bandwidth-per-watt. Apple Silicon dominates 'strict' because the M-series is the perf-per-watt king for inference.

Display currency only. USD is the source-of-truth. FX rates are mid-market, dated, and approximate — actual buying rates may carry a 3-5% spread.

Price versus performance

Price vs performance (budget-neutral)
11 cards · 1 skipped (no price)
0255075100$500$1,000$2,000$4,000$8,000Effective price (log)Performance (budget-neutral)your budgetNVIDIA GeForce RTX 3090 Ti — $1,199 · AvoidNVIDIA RTX PRO 4500 Blackwell — $2,600 · AvoidNVIDIA H100 PCIe — $25,000 · AvoidNVIDIA GeForce RTX 3090 — $899 · Top pickGeForce RTX 3090NVIDIA RTX PRO 4000 Blackwell — $1,500 · Top pickRTX PRO 4000 BlackwellNVIDIA GeForce RTX 4080 — $1,099 · Top pickGeForce RTX 4080NVIDIA GeForce RTX 4080 Super — $1,099 · Top pickGeForce RTX 4080 SuperNVIDIA GeForce RTX 5070 Ti — $849 · Top pickGeForce RTX 5070 TiNVIDIA GeForce RTX 4070 Ti Super — $829 · Top pickGeForce RTX 4070 Ti SuperNVIDIA GeForce RTX 5060 Ti 16GB — $459 · Top pickGeForce RTX 5060 Ti 16GBIntel Arc Pro B60 24GB — $599 · Top pickIntel Arc Pro B60 24GB
Top pick (9)
Avoid (3)

Top GPU picks for your build

Top picks
9 cards matching your stack tightly
Tick two cards to compare side-by-side
Top pick
nvidia24 GB~$899Estimated(used-market price)
Operator-grade

NVIDIA GeForce RTX 3090

Top pick for your setup. With your $1,500 budget on Linux for coding agents, the NVIDIA GeForce RTX 3090 ranks here because 24 GB hits the workable band for coding agents — fits at sensible quants without becoming the bottleneck.

Realistic model class
32B Q4 — estimated starting point; check artifact size and context
Expected throughput
No matched measurement is used for this recommendation. Check the evidence below for the tested model, quantization and runtime.
Evidence
live data · editorial + reproduced community
Editorial
0benchmarks
Reproduced
0community
Stale (>18mo)
0rows
Cohort confidence
—
none
Needs measurement
This recommendation is rule-based, not evidence-backed yet.
  • No benchmarks on file for this hardware.
Help us measure NVIDIA GeForce RTX 3090 →
Featured in stacks
How we scored this card▸

Each dimension is a 0-100 score. The card's position in the ranking is the weighted sum — but we surface tiers, not raw numbers. Bars are sorted by weight (most-influential first).

  • VRAM × workloadweight 22%70Good
  • Budget fitweight 18%95Excellent
  • OS compatibilityweight 16%100Excellent
  • Skill matchweight 10%95Excellent
  • Power headroomweight 8%80Strong
  • Multi-GPU pathweight 8%80Strong
  • Thermal / noiseweight 6%95Excellent
  • Gaming alignmentweight 6%95Excellent
  • Perf-per-wattweight 6%85Strong

Tier mapping: top ≥ 75 composite · alternate 60-74 · acceptable 40-59 · avoid < 40 or over-budget / incompatible.

Caveats
  • •Used-market only — fan/thermal-pad inspection required; new MSRP from launch is no longer the relevant price.
Featured in these stacks
Top pick
nvidia24 GB~$1,500
Operator-grade

NVIDIA RTX PRO 4000 Blackwell

Top pick for your setup. With your $1,500 budget on Linux for coding agents, the NVIDIA RTX PRO 4000 Blackwell ranks here because 24 GB hits the workable band for coding agents — fits at sensible quants without becoming the bottleneck.

Realistic model class
32B Q4 — estimated starting point; check artifact size and context
Expected throughput
No matched measurement is used for this recommendation. Check the evidence below for the tested model, quantization and runtime.
Evidence
live data · editorial + reproduced community
Editorial
0benchmarks
Reproduced
0community
Stale (>18mo)
0rows
Cohort confidence
—
none
Needs measurement
This recommendation is rule-based, not evidence-backed yet.
  • No benchmarks on file for this hardware.
Help us measure NVIDIA RTX PRO 4000 Blackwell →
How we scored this card▸

Each dimension is a 0-100 score. The card's position in the ranking is the weighted sum — but we surface tiers, not raw numbers. Bars are sorted by weight (most-influential first).

  • VRAM × workloadweight 22%70Good
  • Budget fitweight 18%85Strong
  • OS compatibilityweight 16%100Excellent
  • Skill matchweight 10%95Excellent
  • Power headroomweight 8%95Excellent
  • Multi-GPU pathweight 8%80Strong
  • Thermal / noiseweight 6%95Excellent
  • Gaming alignmentweight 6%85Strong
  • Perf-per-wattweight 6%95Excellent

Tier mapping: top ≥ 75 composite · alternate 60-74 · acceptable 40-59 · avoid < 40 or over-budget / incompatible.

Top pick
nvidia24 GB
Operator-grade

NVIDIA GeForce RTX 5090 Mobile

Top pick for your setup. With your $1,500 budget on Linux for coding agents, the NVIDIA GeForce RTX 5090 Mobile ranks here because 24 GB hits the workable band for coding agents — fits at sensible quants without becoming the bottleneck.

Realistic model class
32B Q4 — estimated starting point; check artifact size and context
Expected throughput
No matched measurement is used for this recommendation. Check the evidence below for the tested model, quantization and runtime.
Evidence
live data · editorial + reproduced community
Editorial
0benchmarks
Reproduced
0community
Stale (>18mo)
0rows
Cohort confidence
—
none
Needs measurement
This recommendation is rule-based, not evidence-backed yet.
  • No benchmarks on file for this hardware.
Help us measure NVIDIA GeForce RTX 5090 Mobile →
How we scored this card▸

Each dimension is a 0-100 score. The card's position in the ranking is the weighted sum — but we surface tiers, not raw numbers. Bars are sorted by weight (most-influential first).

  • VRAM × workloadweight 22%70Good
  • Budget fitweight 18%40Acceptable
  • OS compatibilityweight 16%100Excellent
  • Skill matchweight 10%95Excellent
  • Power headroomweight 8%95Excellent
  • Multi-GPU pathweight 8%80Strong
  • Thermal / noiseweight 6%95Excellent
  • Gaming alignmentweight 6%95Excellent
  • Perf-per-wattweight 6%95Excellent

Tier mapping: top ≥ 75 composite · alternate 60-74 · acceptable 40-59 · avoid < 40 or over-budget / incompatible.

Top pick
nvidia16 GB~$1,099
Operator-grade

NVIDIA GeForce RTX 4080

Top pick for your setup. With your $1,500 budget on Linux for coding agents, the NVIDIA GeForce RTX 4080 sits in this tier on a balance of capability, OS compat, power, and budget fit.

Realistic model class
13–14B Q4 — estimated starting point; check artifact size and context
Expected throughput
No matched measurement is used for this recommendation. Check the evidence below for the tested model, quantization and runtime.
Evidence
live data · editorial + reproduced community
Editorial
0benchmarks
Reproduced
0community
Stale (>18mo)
0rows
Cohort confidence
—
none
Needs measurement
This recommendation is rule-based, not evidence-backed yet.
  • No benchmarks on file for this hardware.
Help us measure NVIDIA GeForce RTX 4080 →
How we scored this card▸

Each dimension is a 0-100 score. The card's position in the ranking is the weighted sum — but we surface tiers, not raw numbers. Bars are sorted by weight (most-influential first).

  • VRAM × workloadweight 22%33Weak
  • Budget fitweight 18%95Excellent
  • OS compatibilityweight 16%100Excellent
  • Skill matchweight 10%95Excellent
  • Power headroomweight 8%80Strong
  • Multi-GPU pathweight 8%80Strong
  • Thermal / noiseweight 6%95Excellent
  • Gaming alignmentweight 6%90Excellent
  • Perf-per-wattweight 6%85Strong

Tier mapping: top ≥ 75 composite · alternate 60-74 · acceptable 40-59 · avoid < 40 or over-budget / incompatible.

Caveats
  • •16 GB is below the comfortable VRAM minimum for coding agents — expect quant downgrades or very tight context windows.
Top pick
nvidia16 GB~$1,099
Operator-grade

NVIDIA GeForce RTX 4080 Super

Top pick for your setup. With your $1,500 budget on Linux for coding agents, the NVIDIA GeForce RTX 4080 Super sits in this tier on a balance of capability, OS compat, power, and budget fit.

Realistic model class
13–14B Q4 — estimated starting point; check artifact size and context
Expected throughput
No matched measurement is used for this recommendation. Check the evidence below for the tested model, quantization and runtime.
Evidence
live data · editorial + reproduced community
Editorial
0benchmarks
Reproduced
0community
Stale (>18mo)
0rows
Cohort confidence
—
none
Needs measurement
This recommendation is rule-based, not evidence-backed yet.
  • No benchmarks on file for this hardware.
Help us measure NVIDIA GeForce RTX 4080 Super →
How we scored this card▸

Each dimension is a 0-100 score. The card's position in the ranking is the weighted sum — but we surface tiers, not raw numbers. Bars are sorted by weight (most-influential first).

  • VRAM × workloadweight 22%33Weak
  • Budget fitweight 18%95Excellent
  • OS compatibilityweight 16%100Excellent
  • Skill matchweight 10%95Excellent
  • Power headroomweight 8%80Strong
  • Multi-GPU pathweight 8%80Strong
  • Thermal / noiseweight 6%95Excellent
  • Gaming alignmentweight 6%90Excellent
  • Perf-per-wattweight 6%85Strong

Tier mapping: top ≥ 75 composite · alternate 60-74 · acceptable 40-59 · avoid < 40 or over-budget / incompatible.

Caveats
  • •16 GB is below the comfortable VRAM minimum for coding agents — expect quant downgrades or very tight context windows.
Top pick
nvidia16 GB~$849
Operator-grade

NVIDIA GeForce RTX 5070 Ti

Top pick for your setup. With your $1,500 budget on Linux for coding agents, the NVIDIA GeForce RTX 5070 Ti sits in this tier on a balance of capability, OS compat, power, and budget fit.

Realistic model class
13–14B Q4 — estimated starting point; check artifact size and context
Expected throughput
No matched measurement is used for this recommendation. Check the evidence below for the tested model, quantization and runtime.
Evidence
live data · editorial + reproduced community
Editorial
0benchmarks
Reproduced
0community
Stale (>18mo)
0rows
Cohort confidence
—
none
Needs measurement
This recommendation is rule-based, not evidence-backed yet.
  • No benchmarks on file for this hardware.
Help us measure NVIDIA GeForce RTX 5070 Ti →
How we scored this card▸

Each dimension is a 0-100 score. The card's position in the ranking is the weighted sum — but we surface tiers, not raw numbers. Bars are sorted by weight (most-influential first).

  • VRAM × workloadweight 22%33Weak
  • Budget fitweight 18%95Excellent
  • OS compatibilityweight 16%100Excellent
  • Skill matchweight 10%95Excellent
  • Power headroomweight 8%80Strong
  • Multi-GPU pathweight 8%80Strong
  • Thermal / noiseweight 6%95Excellent
  • Gaming alignmentweight 6%90Excellent
  • Perf-per-wattweight 6%85Strong

Tier mapping: top ≥ 75 composite · alternate 60-74 · acceptable 40-59 · avoid < 40 or over-budget / incompatible.

Caveats
  • •16 GB is below the comfortable VRAM minimum for coding agents — expect quant downgrades or very tight context windows.
Top pick
nvidia16 GB~$829
Operator-grade

NVIDIA GeForce RTX 4070 Ti Super

Top pick for your setup. With your $1,500 budget on Linux for coding agents, the NVIDIA GeForce RTX 4070 Ti Super sits in this tier on a balance of capability, OS compat, power, and budget fit.

Realistic model class
13–14B Q4 — estimated starting point; check artifact size and context
Expected throughput
No matched measurement is used for this recommendation. Check the evidence below for the tested model, quantization and runtime.
Evidence
live data · editorial + reproduced community
Editorial
0benchmarks
Reproduced
0community
Stale (>18mo)
0rows
Cohort confidence
—
none
Needs measurement
This recommendation is rule-based, not evidence-backed yet.
  • No benchmarks on file for this hardware.
Help us measure NVIDIA GeForce RTX 4070 Ti Super →
How we scored this card▸

Each dimension is a 0-100 score. The card's position in the ranking is the weighted sum — but we surface tiers, not raw numbers. Bars are sorted by weight (most-influential first).

  • VRAM × workloadweight 22%33Weak
  • Budget fitweight 18%95Excellent
  • OS compatibilityweight 16%100Excellent
  • Skill matchweight 10%95Excellent
  • Power headroomweight 8%80Strong
  • Multi-GPU pathweight 8%80Strong
  • Thermal / noiseweight 6%95Excellent
  • Gaming alignmentweight 6%90Excellent
  • Perf-per-wattweight 6%85Strong

Tier mapping: top ≥ 75 composite · alternate 60-74 · acceptable 40-59 · avoid < 40 or over-budget / incompatible.

Caveats
  • •16 GB is below the comfortable VRAM minimum for coding agents — expect quant downgrades or very tight context windows.
Top pick
nvidia16 GB~$459
Operator-grade

NVIDIA GeForce RTX 5060 Ti 16GB

Top pick for your setup. With your $1,500 budget on Linux for coding agents, the NVIDIA GeForce RTX 5060 Ti 16GB sits in this tier on a balance of capability, OS compat, power, and budget fit.

Realistic model class
13–14B Q4 — estimated starting point; check artifact size and context
Expected throughput
No matched measurement is used for this recommendation. Check the evidence below for the tested model, quantization and runtime.
Evidence
live data · editorial + reproduced community
Editorial
0benchmarks
Reproduced
0community
Stale (>18mo)
0rows
Cohort confidence
—
none
Needs measurement
This recommendation is rule-based, not evidence-backed yet.
  • No benchmarks on file for this hardware.
Help us measure NVIDIA GeForce RTX 5060 Ti 16GB →
How we scored this card▸

Each dimension is a 0-100 score. The card's position in the ranking is the weighted sum — but we surface tiers, not raw numbers. Bars are sorted by weight (most-influential first).

  • VRAM × workloadweight 22%33Weak
  • Budget fitweight 18%80Strong
  • OS compatibilityweight 16%100Excellent
  • Skill matchweight 10%95Excellent
  • Power headroomweight 8%95Excellent
  • Multi-GPU pathweight 8%80Strong
  • Thermal / noiseweight 6%95Excellent
  • Gaming alignmentweight 6%70Good
  • Perf-per-wattweight 6%95Excellent

Tier mapping: top ≥ 75 composite · alternate 60-74 · acceptable 40-59 · avoid < 40 or over-budget / incompatible.

Caveats
  • •16 GB is below the comfortable VRAM minimum for coding agents — expect quant downgrades or very tight context windows.
Top pick
intel24 GB~$599
Operator-grade

Intel Arc Pro B60 24GB

Top pick for your setup. With your $1,500 budget on Linux for coding agents, the Intel Arc Pro B60 24GB sits in this tier on a balance of capability, OS compat, power, and budget fit.

Realistic model class
32B Q4 — estimated starting point; check artifact size and context
Expected throughput
No matched measurement is used for this recommendation. Check the evidence below for the tested model, quantization and runtime.
Evidence
live data · editorial + reproduced community
Editorial
0benchmarks
Reproduced
0community
Stale (>18mo)
0rows
Cohort confidence
—
none
Needs measurement
This recommendation is rule-based, not evidence-backed yet.
  • No benchmarks on file for this hardware.
Help us measure Intel Arc Pro B60 24GB →
How we scored this card▸

Each dimension is a 0-100 score. The card's position in the ranking is the weighted sum — but we surface tiers, not raw numbers. Bars are sorted by weight (most-influential first).

  • VRAM × workloadweight 22%65Good
  • Budget fitweight 18%80Strong
  • OS compatibilityweight 16%70Good
  • Skill matchweight 10%55Acceptable
  • Power headroomweight 8%95Excellent
  • Multi-GPU pathweight 8%80Strong
  • Thermal / noiseweight 6%95Excellent
  • Gaming alignmentweight 6%85Strong
  • Perf-per-wattweight 6%95Excellent

Tier mapping: top ≥ 75 composite · alternate 60-74 · acceptable 40-59 · avoid < 40 or over-budget / incompatible.

Caveats
  • •Intel discrete GPU AI tooling lags NVIDIA — runtime support exists (IPEX-LLM) but documentation is thinner.

GPUs we ruled out

Why we ruled these out
Over-budget or fundamentally incompatible — listed for the upgrade-path conversation