L
localai.computer
ModelsGPUsSystemsAI SetupsBuildsOpenClawMethodology

Resources

  • Methodology
  • Submit Benchmark
  • About

Browse

  • AI Models
  • GPUs
  • PC Builds

Guides

  • OpenClaw Guide
  • How-To Guides

Legal

  • Privacy
  • Terms
  • Contact

© 2025 localai.computer. Hardware recommendations for running AI models locally.

ℹ️We earn from qualifying purchases through affiliate links at no extra cost to you. This supports our free content and research.

  1. Home
  2. GPUs
  3. RTX 5090

Quick Answer: RTX 5090 offers 32GB VRAM and starts around $5196.32. It delivers approximately 396 tokens/sec on bigcode/starcoder2-3b. It typically draws 575W under load.

RTX 5090

Unknown
By NVIDIAReleased 2025-01MSRP $1,999.00

This GPU offers reliable throughput for local AI workloads. Pair it with the right model quantization to hit your desired tokens/sec, and monitor prices below to catch the best deal.

Buy on Amazon - $5,196.32View Benchmarks
Specs snapshot
Key hardware metrics for AI workloads.
VRAM32GB
Cores21,760
TDP575W
ArchitectureBlackwell
Key Takeaways
  • 32GB VRAM - runs models up to ~80B parameters
  • Flagship-class compute for maximum throughput
  • High power draw (575W) - requires robust PSU (850W+ recommended)
  • Strong price-to-VRAM value

What this means for you

With 32GB VRAM, RTX 5090 can run models up to approximately 80B parameters using 4-bit quantization. This handles most popular models including Llama 3 70B, Mistral 7B, and larger.

Who should buy

  • Running 70B parameter models at good speeds
  • Multiple model instances simultaneously
  • Production deployments on single GPU

Looking to upgrade?

Consider RTX 4090 or RTX 6000 Ada — 24GB Ada offers better efficiency than Ampere.

Where to Buy

Buy directly on Amazon with fast shipping and reliable customer service.

💰Price Analysis
Good price range.
Current Price
RTX 5090
$52
Buy on Amazon
+6.0% over 30 days
30-day low
$454
30-day avg
$507
30-day high
$542
DEALNear lowest price! ($454)
Get email when price drops
AmazonUnknown
$5,196.32
Check availability
Buy on Amazon

Prime shipping available • 30-day returns

More Amazon options

Rotate out primary variants whenever validation flags an issue.

Complete Your Build

Essential accessories to pair with RTX 5090

Corsair RM750x (2025) 750W
Minimum 750W recommended for RTX 40 series
$119
Find on Amazon
Corsair Vengeance 32GB DDR5-6000
32GB ideal for AI workloads
$129
Find on Amazon
Noctua NF-A12x25 PWM
Quiet and efficient cooling
$35
Find on Amazon
Thermal Grizzly Kryonaut
Premium thermal paste for optimal cooling
$15
Find on Amazon

Total Bundle Price

All items from Amazon

$350
Individual: $350
Find All on AmazonMore GPUs

💡 Not ready to buy? Try cloud GPUs first

Test RTX 5090 performance in the cloud before investing in hardware. Pay by the hour with no commitment.

Vast.aifrom $0.20/hrRunPodfrom $0.30/hrLambda Labsenterprise-grade

AI benchmarks

ModelQuantizationTokens/secVRAM used
bigcode/starcoder2-3bQ4
395.58 tok/sEstimated

Auto-generated benchmark

2GB
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q4
394.56 tok/sEstimated

Auto-generated benchmark

1GB
LiquidAI/LFM2-1.2BQ4
394.12 tok/sEstimated

Auto-generated benchmark

1GB
google-bert/bert-base-uncasedQ4
393.79 tok/sEstimated

Auto-generated benchmark

1GB
tencent/HunyuanOCRQ4
393.19 tok/sEstimated

Auto-generated benchmark

1GB
google/gemma-2-2b-itQ4
390.12 tok/sEstimated

Auto-generated benchmark

1GB
inference-net/Schematron-3BQ4
389.59 tok/sEstimated

Auto-generated benchmark

2GB
meta-llama/Llama-3.2-3B-InstructQ4
387.38 tok/sEstimated

Auto-generated benchmark

2GB
ibm-research/PowerMoE-3bQ4
383.95 tok/sEstimated

Auto-generated benchmark

2GB
allenai/OLMo-2-0425-1BQ4
382.28 tok/sEstimated

Auto-generated benchmark

1GB
meta-llama/Llama-Guard-3-1BQ4
380.84 tok/sEstimated

Auto-generated benchmark

1GB
WeiboAI/VibeThinker-1.5BQ4
376.34 tok/sEstimated

Auto-generated benchmark

1GB
deepseek-ai/deepseek-coder-1.3b-instructQ4
371.04 tok/sEstimated

Auto-generated benchmark

2GB
meta-llama/Llama-3.2-1B-InstructQ4
369.32 tok/sEstimated

Auto-generated benchmark

1GB
Qwen/Qwen3-ASR-1.7BQ4
367.70 tok/sEstimated

Auto-generated benchmark

2GB
nari-labs/Dia2-2BQ4
366.36 tok/sEstimated

Auto-generated benchmark

2GB
Qwen/Qwen2.5-3B-InstructQ4
362.86 tok/sEstimated

Auto-generated benchmark

2GB
Qwen/Qwen2.5-3BQ4
360.59 tok/sEstimated

Auto-generated benchmark

2GB
deepseek-ai/DeepSeek-OCR-2Q4
360.17 tok/sEstimated

Auto-generated benchmark

2GB
apple/OpenELM-1_1B-InstructQ4
359.92 tok/sEstimated

Auto-generated benchmark

1GB
deepseek-ai/DeepSeek-OCRQ4
357.55 tok/sEstimated

Auto-generated benchmark

2GB
google/gemma-2bQ4
355.97 tok/sEstimated

Auto-generated benchmark

1GB
google-t5/t5-3bQ4
354.58 tok/sEstimated

Auto-generated benchmark

2GB
meta-llama/Llama-3.2-3BQ4
349.12 tok/sEstimated

Auto-generated benchmark

2GB
unsloth/gemma-3-1b-itQ4
343.32 tok/sEstimated

Auto-generated benchmark

1GB
unsloth/Llama-3.2-1B-InstructQ4
340.86 tok/sEstimated

Auto-generated benchmark

1GB
google/embeddinggemma-300mQ4
336.60 tok/sEstimated

Auto-generated benchmark

1GB
google/gemma-3-1b-itQ4
334.93 tok/sEstimated

Auto-generated benchmark

1GB
nineninesix/kani-tts-2-enQ4
333.47 tok/sEstimated

Auto-generated benchmark

1GB
facebook/sam3Q4
332.76 tok/sEstimated

Auto-generated benchmark

1GB
ibm-granite/granite-3.3-2b-instructQ4
332.41 tok/sEstimated

Auto-generated benchmark

1GB
Qwen/Qwen3-0.6B-BaseQ4
329.64 tok/sEstimated

Auto-generated benchmark

3GB
unsloth/Meta-Llama-3.1-8B-InstructQ4
329.16 tok/sEstimated

Auto-generated benchmark

4GB
meta-llama/Llama-Guard-3-8BQ4
329.11 tok/sEstimated

Auto-generated benchmark

4GB
deepseek-ai/DeepSeek-R1-Distill-Qwen-7BQ4
328.93 tok/sEstimated

Auto-generated benchmark

4GB
Nanbeige/Nanbeige4.1-3BQ4
328.74 tok/sEstimated

Auto-generated benchmark

3GB
unsloth/mistral-7b-v0.3-bnb-4bitQ4
328.65 tok/sEstimated

Auto-generated benchmark

4GB
Qwen/Qwen3-4B-Thinking-2507Q4
328.58 tok/sEstimated

Auto-generated benchmark

2GB
context-labs/meta-llama-Llama-3.2-3B-Instruct-FP16Q4
328.24 tok/sEstimated

Auto-generated benchmark

2GB
FireRedTeam/FireRed-Image-Edit-1.0Q4
328.02 tok/sEstimated

Auto-generated benchmark

4GB
unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bitQ4
328.00 tok/sEstimated

Auto-generated benchmark

4GB
MiniMaxAI/MiniMax-M2.5Q4
327.59 tok/sEstimated

Auto-generated benchmark

4GB
microsoft/phi-4Q4
327.31 tok/sEstimated

Auto-generated benchmark

4GB
meta-llama/Llama-3.2-1BQ4
326.61 tok/sEstimated

Auto-generated benchmark

1GB
tencent/HunyuanVideo-1.5Q4
326.43 tok/sEstimated

Auto-generated benchmark

4GB
Qwen/Qwen3-4B-Instruct-2507Q4
326.24 tok/sEstimated

Auto-generated benchmark

2GB
microsoft/Phi-3.5-vision-instructQ4
325.38 tok/sEstimated

Auto-generated benchmark

4GB
nvidia/personaplex-7b-v1Q4
325.16 tok/sEstimated

Auto-generated benchmark

4GB
openai-community/gpt2-largeQ4
324.95 tok/sEstimated

Auto-generated benchmark

4GB
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bitQ4
324.67 tok/sEstimated

Auto-generated benchmark

2GB
bigcode/starcoder2-3b
Q4
2GB
395.58 tok/sEstimated
Auto-generated benchmark
TinyLlama/TinyLlama-1.1B-Chat-v1.0
Q4
1GB
394.56 tok/sEstimated
Auto-generated benchmark
LiquidAI/LFM2-1.2B
Q4
1GB
394.12 tok/sEstimated
Auto-generated benchmark
google-bert/bert-base-uncased
Q4
1GB
393.79 tok/sEstimated
Auto-generated benchmark
tencent/HunyuanOCR
Q4
1GB
393.19 tok/sEstimated
Auto-generated benchmark
google/gemma-2-2b-it
Q4
1GB
390.12 tok/sEstimated
Auto-generated benchmark
inference-net/Schematron-3B
Q4
2GB
389.59 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-3B-Instruct
Q4
2GB
387.38 tok/sEstimated
Auto-generated benchmark
ibm-research/PowerMoE-3b
Q4
2GB
383.95 tok/sEstimated
Auto-generated benchmark
allenai/OLMo-2-0425-1B
Q4
1GB
382.28 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-Guard-3-1B
Q4
1GB
380.84 tok/sEstimated
Auto-generated benchmark
WeiboAI/VibeThinker-1.5B
Q4
1GB
376.34 tok/sEstimated
Auto-generated benchmark
deepseek-ai/deepseek-coder-1.3b-instruct
Q4
2GB
371.04 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-1B-Instruct
Q4
1GB
369.32 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen3-ASR-1.7B
Q4
2GB
367.70 tok/sEstimated
Auto-generated benchmark
nari-labs/Dia2-2B
Q4
2GB
366.36 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen2.5-3B-Instruct
Q4
2GB
362.86 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen2.5-3B
Q4
2GB
360.59 tok/sEstimated
Auto-generated benchmark
deepseek-ai/DeepSeek-OCR-2
Q4
2GB
360.17 tok/sEstimated
Auto-generated benchmark
apple/OpenELM-1_1B-Instruct
Q4
1GB
359.92 tok/sEstimated
Auto-generated benchmark
deepseek-ai/DeepSeek-OCR
Q4
2GB
357.55 tok/sEstimated
Auto-generated benchmark
google/gemma-2b
Q4
1GB
355.97 tok/sEstimated
Auto-generated benchmark
google-t5/t5-3b
Q4
2GB
354.58 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-3B
Q4
2GB
349.12 tok/sEstimated
Auto-generated benchmark
unsloth/gemma-3-1b-it
Q4
1GB
343.32 tok/sEstimated
Auto-generated benchmark
unsloth/Llama-3.2-1B-Instruct
Q4
1GB
340.86 tok/sEstimated
Auto-generated benchmark
google/embeddinggemma-300m
Q4
1GB
336.60 tok/sEstimated
Auto-generated benchmark
google/gemma-3-1b-it
Q4
1GB
334.93 tok/sEstimated
Auto-generated benchmark
nineninesix/kani-tts-2-en
Q4
1GB
333.47 tok/sEstimated
Auto-generated benchmark
facebook/sam3
Q4
1GB
332.76 tok/sEstimated
Auto-generated benchmark
ibm-granite/granite-3.3-2b-instruct
Q4
1GB
332.41 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen3-0.6B-Base
Q4
3GB
329.64 tok/sEstimated
Auto-generated benchmark
unsloth/Meta-Llama-3.1-8B-Instruct
Q4
4GB
329.16 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-Guard-3-8B
Q4
4GB
329.11 tok/sEstimated
Auto-generated benchmark
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Q4
4GB
328.93 tok/sEstimated
Auto-generated benchmark
Nanbeige/Nanbeige4.1-3B
Q4
3GB
328.74 tok/sEstimated
Auto-generated benchmark
unsloth/mistral-7b-v0.3-bnb-4bit
Q4
4GB
328.65 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen3-4B-Thinking-2507
Q4
2GB
328.58 tok/sEstimated
Auto-generated benchmark
context-labs/meta-llama-Llama-3.2-3B-Instruct-FP16
Q4
2GB
328.24 tok/sEstimated
Auto-generated benchmark
FireRedTeam/FireRed-Image-Edit-1.0
Q4
4GB
328.02 tok/sEstimated
Auto-generated benchmark
unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
Q4
4GB
328.00 tok/sEstimated
Auto-generated benchmark
MiniMaxAI/MiniMax-M2.5
Q4
4GB
327.59 tok/sEstimated
Auto-generated benchmark
microsoft/phi-4
Q4
4GB
327.31 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-1B
Q4
1GB
326.61 tok/sEstimated
Auto-generated benchmark
tencent/HunyuanVideo-1.5
Q4
4GB
326.43 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen3-4B-Instruct-2507
Q4
2GB
326.24 tok/sEstimated
Auto-generated benchmark
microsoft/Phi-3.5-vision-instruct
Q4
4GB
325.38 tok/sEstimated
Auto-generated benchmark
nvidia/personaplex-7b-v1
Q4
4GB
325.16 tok/sEstimated
Auto-generated benchmark
openai-community/gpt2-large
Q4
4GB
324.95 tok/sEstimated
Auto-generated benchmark
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bit
Q4
2GB
324.67 tok/sEstimated
Auto-generated benchmark

Note: Performance estimates are calculated. Real results may vary. Methodology · Submit real data

Model compatibility

ModelQuantizationVerdictEstimated speedVRAM needed
openai-community/gpt2Q8Fits comfortably
219.09 tok/sEstimated
7GB (have 32GB)
openai-community/gpt2FP16Fits comfortably
120.80 tok/sEstimated
15GB (have 32GB)
Qwen/Qwen2.5-7B-InstructQ4Fits comfortably
292.61 tok/sEstimated
4GB (have 32GB)
Qwen/Qwen2.5-7B-InstructQ8Fits comfortably
190.82 tok/sEstimated
7GB (have 32GB)
Qwen/Qwen2.5-7B-InstructFP16Fits comfortably
111.68 tok/sEstimated
15GB (have 32GB)
Qwen/Qwen3-0.6BQ4Fits comfortably
292.73 tok/sEstimated
3GB (have 32GB)
Qwen/Qwen3-0.6BQ8Fits comfortably
202.05 tok/sEstimated
6GB (have 32GB)
Qwen/Qwen3-0.6BFP16Fits comfortably
117.98 tok/sEstimated
13GB (have 32GB)
Gensyn/Qwen2.5-0.5B-InstructQ4Fits comfortably
288.38 tok/sEstimated
3GB (have 32GB)
Gensyn/Qwen2.5-0.5B-InstructQ8Fits comfortably
211.59 tok/sEstimated
5GB (have 32GB)
Gensyn/Qwen2.5-0.5B-InstructFP16Fits comfortably
113.11 tok/sEstimated
11GB (have 32GB)
meta-llama/Llama-3.1-8B-InstructQ4Fits comfortably
282.68 tok/sEstimated
4GB (have 32GB)
meta-llama/Llama-3.1-8B-InstructQ8Fits comfortably
221.18 tok/sEstimated
9GB (have 32GB)
meta-llama/Llama-3.1-8B-InstructFP16Fits comfortably
107.34 tok/sEstimated
17GB (have 32GB)
dphn/dolphin-2.9.1-yi-1.5-34bQ4Fits comfortably
106.58 tok/sEstimated
17GB (have 32GB)
dphn/dolphin-2.9.1-yi-1.5-34bQ8Not supported
74.38 tok/sEstimated
35GB (have 32GB)
dphn/dolphin-2.9.1-yi-1.5-34bFP16Not supported
41.37 tok/sEstimated
70GB (have 32GB)
openai/gpt-oss-20bQ4Fits comfortably
156.71 tok/sEstimated
10GB (have 32GB)
openai/gpt-oss-20bQ8Fits comfortably
126.70 tok/sEstimated
20GB (have 32GB)
openai/gpt-oss-20bFP16Not supported
58.13 tok/sEstimated
41GB (have 32GB)
google/gemma-3-1b-itQ4Fits comfortably
334.93 tok/sEstimated
1GB (have 32GB)
google/gemma-3-1b-itQ8Fits comfortably
234.59 tok/sEstimated
1GB (have 32GB)
google/gemma-3-1b-itFP16Fits comfortably
132.99 tok/sEstimated
2GB (have 32GB)
Qwen/Qwen3-Embedding-0.6BQ4Fits comfortably
318.55 tok/sEstimated
3GB (have 32GB)
Qwen/Qwen3-Embedding-0.6BQ8Fits comfortably
212.04 tok/sEstimated
6GB (have 32GB)
Qwen/Qwen3-Embedding-0.6BFP16Fits comfortably
122.74 tok/sEstimated
13GB (have 32GB)
Qwen/Qwen2.5-1.5B-InstructQ4Fits comfortably
307.95 tok/sEstimated
3GB (have 32GB)
Qwen/Qwen2.5-1.5B-InstructQ8Fits comfortably
220.62 tok/sEstimated
5GB (have 32GB)
Qwen/Qwen2.5-1.5B-InstructFP16Fits comfortably
120.79 tok/sEstimated
11GB (have 32GB)
facebook/opt-125mQ4Fits comfortably
320.49 tok/sEstimated
4GB (have 32GB)
facebook/opt-125mQ8Fits comfortably
222.22 tok/sEstimated
7GB (have 32GB)
facebook/opt-125mFP16Fits comfortably
120.48 tok/sEstimated
15GB (have 32GB)
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q4Fits comfortably
394.56 tok/sEstimated
1GB (have 32GB)
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q8Fits comfortably
234.41 tok/sEstimated
1GB (have 32GB)
TinyLlama/TinyLlama-1.1B-Chat-v1.0FP16Fits comfortably
134.28 tok/sEstimated
2GB (have 32GB)
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q4Fits comfortably
307.74 tok/sEstimated
4GB (have 32GB)
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q8Fits comfortably
226.70 tok/sEstimated
7GB (have 32GB)
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5FP16Fits comfortably
113.49 tok/sEstimated
15GB (have 32GB)
Qwen/Qwen3-4B-Instruct-2507Q4Fits comfortably
326.24 tok/sEstimated
2GB (have 32GB)
Qwen/Qwen3-4B-Instruct-2507Q8Fits comfortably
227.93 tok/sEstimated
4GB (have 32GB)
Qwen/Qwen3-4B-Instruct-2507FP16Fits comfortably
104.72 tok/sEstimated
9GB (have 32GB)
meta-llama/Llama-3.2-1B-InstructQ4Fits comfortably
369.32 tok/sEstimated
1GB (have 32GB)
meta-llama/Llama-3.2-1B-InstructQ8Fits comfortably
267.55 tok/sEstimated
1GB (have 32GB)
meta-llama/Llama-3.2-1B-InstructFP16Fits comfortably
143.68 tok/sEstimated
2GB (have 32GB)
openai/gpt-oss-120bQ4Not supported
62.12 tok/sEstimated
59GB (have 32GB)
openai/gpt-oss-120bQ8Not supported
41.62 tok/sEstimated
117GB (have 32GB)
openai/gpt-oss-120bFP16Not supported
20.83 tok/sEstimated
235GB (have 32GB)
Qwen/Qwen2.5-3B-InstructQ4Fits comfortably
362.86 tok/sEstimated
2GB (have 32GB)
Qwen/Qwen2.5-3B-InstructQ8Fits comfortably
241.79 tok/sEstimated
3GB (have 32GB)
openai-community/gpt2Q4Fits comfortably
318.80 tok/sEstimated
4GB (have 32GB)
openai-community/gpt2Q8
Fits comfortably7GB required · 32GB available
219.09 tok/sEstimated
openai-community/gpt2FP16
Fits comfortably15GB required · 32GB available
120.80 tok/sEstimated
Qwen/Qwen2.5-7B-InstructQ4
Fits comfortably4GB required · 32GB available
292.61 tok/sEstimated
Qwen/Qwen2.5-7B-InstructQ8
Fits comfortably7GB required · 32GB available
190.82 tok/sEstimated
Qwen/Qwen2.5-7B-InstructFP16
Fits comfortably15GB required · 32GB available
111.68 tok/sEstimated
Qwen/Qwen3-0.6BQ4
Fits comfortably3GB required · 32GB available
292.73 tok/sEstimated
Qwen/Qwen3-0.6BQ8
Fits comfortably6GB required · 32GB available
202.05 tok/sEstimated
Qwen/Qwen3-0.6BFP16
Fits comfortably13GB required · 32GB available
117.98 tok/sEstimated
Gensyn/Qwen2.5-0.5B-InstructQ4
Fits comfortably3GB required · 32GB available
288.38 tok/sEstimated
Gensyn/Qwen2.5-0.5B-InstructQ8
Fits comfortably5GB required · 32GB available
211.59 tok/sEstimated
Gensyn/Qwen2.5-0.5B-InstructFP16
Fits comfortably11GB required · 32GB available
113.11 tok/sEstimated
meta-llama/Llama-3.1-8B-InstructQ4
Fits comfortably4GB required · 32GB available
282.68 tok/sEstimated
meta-llama/Llama-3.1-8B-InstructQ8
Fits comfortably9GB required · 32GB available
221.18 tok/sEstimated
meta-llama/Llama-3.1-8B-InstructFP16
Fits comfortably17GB required · 32GB available
107.34 tok/sEstimated
dphn/dolphin-2.9.1-yi-1.5-34bQ4
Fits comfortably17GB required · 32GB available
106.58 tok/sEstimated
dphn/dolphin-2.9.1-yi-1.5-34bQ8
Not supported35GB required · 32GB available
74.38 tok/sEstimated
dphn/dolphin-2.9.1-yi-1.5-34bFP16
Not supported70GB required · 32GB available
41.37 tok/sEstimated
openai/gpt-oss-20bQ4
Fits comfortably10GB required · 32GB available
156.71 tok/sEstimated
openai/gpt-oss-20bQ8
Fits comfortably20GB required · 32GB available
126.70 tok/sEstimated
openai/gpt-oss-20bFP16
Not supported41GB required · 32GB available
58.13 tok/sEstimated
google/gemma-3-1b-itQ4
Fits comfortably1GB required · 32GB available
334.93 tok/sEstimated
google/gemma-3-1b-itQ8
Fits comfortably1GB required · 32GB available
234.59 tok/sEstimated
google/gemma-3-1b-itFP16
Fits comfortably2GB required · 32GB available
132.99 tok/sEstimated
Qwen/Qwen3-Embedding-0.6BQ4
Fits comfortably3GB required · 32GB available
318.55 tok/sEstimated
Qwen/Qwen3-Embedding-0.6BQ8
Fits comfortably6GB required · 32GB available
212.04 tok/sEstimated
Qwen/Qwen3-Embedding-0.6BFP16
Fits comfortably13GB required · 32GB available
122.74 tok/sEstimated
Qwen/Qwen2.5-1.5B-InstructQ4
Fits comfortably3GB required · 32GB available
307.95 tok/sEstimated
Qwen/Qwen2.5-1.5B-InstructQ8
Fits comfortably5GB required · 32GB available
220.62 tok/sEstimated
Qwen/Qwen2.5-1.5B-InstructFP16
Fits comfortably11GB required · 32GB available
120.79 tok/sEstimated
facebook/opt-125mQ4
Fits comfortably4GB required · 32GB available
320.49 tok/sEstimated
facebook/opt-125mQ8
Fits comfortably7GB required · 32GB available
222.22 tok/sEstimated
facebook/opt-125mFP16
Fits comfortably15GB required · 32GB available
120.48 tok/sEstimated
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q4
Fits comfortably1GB required · 32GB available
394.56 tok/sEstimated
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q8
Fits comfortably1GB required · 32GB available
234.41 tok/sEstimated
TinyLlama/TinyLlama-1.1B-Chat-v1.0FP16
Fits comfortably2GB required · 32GB available
134.28 tok/sEstimated
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q4
Fits comfortably4GB required · 32GB available
307.74 tok/sEstimated
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q8
Fits comfortably7GB required · 32GB available
226.70 tok/sEstimated
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5FP16
Fits comfortably15GB required · 32GB available
113.49 tok/sEstimated
Qwen/Qwen3-4B-Instruct-2507Q4
Fits comfortably2GB required · 32GB available
326.24 tok/sEstimated
Qwen/Qwen3-4B-Instruct-2507Q8
Fits comfortably4GB required · 32GB available
227.93 tok/sEstimated
Qwen/Qwen3-4B-Instruct-2507FP16
Fits comfortably9GB required · 32GB available
104.72 tok/sEstimated
meta-llama/Llama-3.2-1B-InstructQ4
Fits comfortably1GB required · 32GB available
369.32 tok/sEstimated
meta-llama/Llama-3.2-1B-InstructQ8
Fits comfortably1GB required · 32GB available
267.55 tok/sEstimated
meta-llama/Llama-3.2-1B-InstructFP16
Fits comfortably2GB required · 32GB available
143.68 tok/sEstimated
openai/gpt-oss-120bQ4
Not supported59GB required · 32GB available
62.12 tok/sEstimated
openai/gpt-oss-120bQ8
Not supported117GB required · 32GB available
41.62 tok/sEstimated
openai/gpt-oss-120bFP16
Not supported235GB required · 32GB available
20.83 tok/sEstimated
Qwen/Qwen2.5-3B-InstructQ4
Fits comfortably2GB required · 32GB available
362.86 tok/sEstimated
Qwen/Qwen2.5-3B-InstructQ8
Fits comfortably3GB required · 32GB available
241.79 tok/sEstimated
openai-community/gpt2Q4
Fits comfortably4GB required · 32GB available
318.80 tok/sEstimated

Note: Performance estimates are calculated. Real results may vary. Methodology · Submit real data

Alternative GPUs

RTX 5070
12GB

Explore how RTX 5070 stacks up for local inference workloads.

RTX 4060 Ti 16GB
16GB

Explore how RTX 4060 Ti 16GB stacks up for local inference workloads.

RX 6800 XT
16GB

Explore how RX 6800 XT stacks up for local inference workloads.

RTX 4070 Super
12GB

Explore how RTX 4070 Super stacks up for local inference workloads.

RTX 3080
10GB

Explore how RTX 3080 stacks up for local inference workloads.

Can it play popular games?

Cyberpunk 2077
8GB VRAM

RPG • 2020

Baldur's Gate 3
8GB VRAM

RPG • 2023

Hogwarts Legacy
12GB VRAM

Action RPG • 2023

Starfield
8GB VRAM

RPG • 2023

Alan Wake 2
12GB VRAM

Survival Horror • 2023

Elden Ring
8GB VRAM

Action RPG • 2022

Black Myth: Wukong
12GB VRAM

Action RPG • 2024

Grand Theft Auto VI
12GB VRAM

Action Adventure • 2025

Resident Evil 4 Remake
12GB VRAM

Survival Horror • 2023

Marvel's Spider-Man Remastered
12GB VRAM

Action • 2022

The Last of Us Part I
12GB VRAM

Action Adventure • 2023

Red Dead Redemption 2
8GB VRAM

Action Adventure • 2019

View all 64 compatible games