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. RX 7600

Quick Answer: RX 7600 offers 8GB VRAM and starts around $459.00. It delivers approximately 60 tokens/sec on deepseek-ai/DeepSeek-OCR-2. It typically draws 165W under load.

RX 7600

In Stock
By AMDReleased 2023-05MSRP $269.00

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 - $459.00View Benchmarks
Specs snapshot
Key hardware metrics for AI workloads.
VRAM8GB
Cores2,048
TDP165W
ArchitectureRDNA 3
Key Takeaways
  • 8GB VRAM - runs models up to ~20B parameters
  • Efficient (165W) - works with standard PSU configurations
  • Strong price-to-VRAM value

What this means for you

With 8GB VRAM, RX 7600 can run models up to approximately 20B parameters using 4-bit quantization. This is suitable for 7B-13B models like Llama 3 8B, Mistral 7B, and Qwen 7B.

Who should buy

  • Running 7B parameter models with quantization
  • Entry-level local AI exploration

Looking to upgrade?

Consider RTX 4070 or RTX 4080 — Significant performance increase for AI workloads.

Where to Buy

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

💰Price Analysis
Good price range.
Current Price
RX 7600
$5
Buy on Amazon
+8.2% over 30 days
30-day low
$457
30-day avg
$508
30-day high
$543
DEALNear lowest price! ($457)
Get email when price drops
AmazonIn Stock
$459.00
In stock
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 RX 7600

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

$303
Individual: $303
Find All on AmazonMore GPUs

💡 Not ready to buy? Try cloud GPUs first

Test RX 7600 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
deepseek-ai/DeepSeek-OCR-2Q4
59.53 tok/sEstimated

Auto-generated benchmark

2GB
google-t5/t5-3bQ4
58.17 tok/sEstimated

Auto-generated benchmark

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

Auto-generated benchmark

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

Auto-generated benchmark

1GB
unsloth/gemma-3-1b-itQ4
57.82 tok/sEstimated

Auto-generated benchmark

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

Auto-generated benchmark

2GB
google-bert/bert-base-uncasedQ4
57.30 tok/sEstimated

Auto-generated benchmark

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

Auto-generated benchmark

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

Auto-generated benchmark

2GB
unsloth/Llama-3.2-3B-InstructQ4
56.47 tok/sEstimated

Auto-generated benchmark

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

Auto-generated benchmark

2GB
nineninesix/kani-tts-2-enQ4
56.17 tok/sEstimated

Auto-generated benchmark

1GB
facebook/sam3Q4
56.11 tok/sEstimated

Auto-generated benchmark

1GB
tencent/HunyuanOCRQ4
55.11 tok/sEstimated

Auto-generated benchmark

1GB
meta-llama/Llama-3.2-1BQ4
54.73 tok/sEstimated

Auto-generated benchmark

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

Auto-generated benchmark

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

Auto-generated benchmark

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

Auto-generated benchmark

1GB
bigcode/starcoder2-3bQ4
53.88 tok/sEstimated

Auto-generated benchmark

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

Auto-generated benchmark

1GB
meta-llama/Llama-3.2-3B-InstructQ4
53.48 tok/sEstimated

Auto-generated benchmark

2GB
google/gemma-3-1b-itQ4
52.57 tok/sEstimated

Auto-generated benchmark

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

Auto-generated benchmark

1GB
Qwen/Qwen2.5-3BQ4
51.86 tok/sEstimated

Auto-generated benchmark

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

Auto-generated benchmark

2GB
google/embeddinggemma-300mQ4
50.92 tok/sEstimated

Auto-generated benchmark

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

Auto-generated benchmark

1GB
google/gemma-2bQ4
49.27 tok/sEstimated

Auto-generated benchmark

1GB
ibm-research/PowerMoE-3bQ4
49.15 tok/sEstimated

Auto-generated benchmark

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

Auto-generated benchmark

2GB
meta-llama/Llama-Guard-3-1BQ4
48.89 tok/sEstimated

Auto-generated benchmark

1GB
Qwen/Qwen2.5-7B-InstructQ4
48.56 tok/sEstimated

Auto-generated benchmark

4GB
ibm-granite/granite-docling-258MQ4
48.53 tok/sEstimated

Auto-generated benchmark

4GB
zai-org/GLM-4.5-AirQ4
48.42 tok/sEstimated

Auto-generated benchmark

4GB
unsloth/Llama-3.2-1B-InstructQ4
48.33 tok/sEstimated

Auto-generated benchmark

1GB
openai-community/gpt2Q4
48.29 tok/sEstimated

Auto-generated benchmark

4GB
bigscience/bloomz-560mQ4
48.27 tok/sEstimated

Auto-generated benchmark

4GB
Qwen/Qwen3-4B-Thinking-2507-FP8Q4
48.24 tok/sEstimated

Auto-generated benchmark

2GB
Qwen/Qwen3-0.6BQ4
48.16 tok/sEstimated

Auto-generated benchmark

3GB
vikhyatk/moondream2Q4
48.11 tok/sEstimated

Auto-generated benchmark

4GB
Qwen/Qwen2.5-1.5B-InstructQ4
48.04 tok/sEstimated

Auto-generated benchmark

3GB
Qwen/Qwen2.5-0.5BQ4
48.01 tok/sEstimated

Auto-generated benchmark

3GB
black-forest-labs/FLUX.1-devQ4
47.99 tok/sEstimated

Auto-generated benchmark

4GB
lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-8bitQ4
47.96 tok/sEstimated

Auto-generated benchmark

4GB
sshleifer/tiny-gpt2Q4
47.95 tok/sEstimated

Auto-generated benchmark

4GB
ibm-granite/granite-3.3-8b-instructQ4
47.94 tok/sEstimated

Auto-generated benchmark

4GB
xgen-universe/CapybaraQ4
47.94 tok/sEstimated

Auto-generated benchmark

4GB
apple/OpenELM-1_1B-InstructQ4
47.94 tok/sEstimated

Auto-generated benchmark

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

Auto-generated benchmark

2GB
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5BQ4
47.60 tok/sEstimated

Auto-generated benchmark

3GB
deepseek-ai/DeepSeek-OCR-2
Q4
2GB
59.53 tok/sEstimated
Auto-generated benchmark
google-t5/t5-3b
Q4
2GB
58.17 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-1B-Instruct
Q4
1GB
57.97 tok/sEstimated
Auto-generated benchmark
WeiboAI/VibeThinker-1.5B
Q4
1GB
57.89 tok/sEstimated
Auto-generated benchmark
unsloth/gemma-3-1b-it
Q4
1GB
57.82 tok/sEstimated
Auto-generated benchmark
deepseek-ai/deepseek-coder-1.3b-instruct
Q4
2GB
57.57 tok/sEstimated
Auto-generated benchmark
google-bert/bert-base-uncased
Q4
1GB
57.30 tok/sEstimated
Auto-generated benchmark
google/gemma-2-2b-it
Q4
1GB
57.19 tok/sEstimated
Auto-generated benchmark
deepseek-ai/DeepSeek-OCR
Q4
2GB
56.79 tok/sEstimated
Auto-generated benchmark
unsloth/Llama-3.2-3B-Instruct
Q4
2GB
56.47 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen2.5-3B-Instruct
Q4
2GB
56.27 tok/sEstimated
Auto-generated benchmark
nineninesix/kani-tts-2-en
Q4
1GB
56.17 tok/sEstimated
Auto-generated benchmark
facebook/sam3
Q4
1GB
56.11 tok/sEstimated
Auto-generated benchmark
tencent/HunyuanOCR
Q4
1GB
55.11 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-1B
Q4
1GB
54.73 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen3-ASR-1.7B
Q4
2GB
54.22 tok/sEstimated
Auto-generated benchmark
context-labs/meta-llama-Llama-3.2-3B-Instruct-FP16
Q4
2GB
54.15 tok/sEstimated
Auto-generated benchmark
allenai/OLMo-2-0425-1B
Q4
1GB
54.12 tok/sEstimated
Auto-generated benchmark
bigcode/starcoder2-3b
Q4
2GB
53.88 tok/sEstimated
Auto-generated benchmark
TinyLlama/TinyLlama-1.1B-Chat-v1.0
Q4
1GB
53.73 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-3B-Instruct
Q4
2GB
53.48 tok/sEstimated
Auto-generated benchmark
google/gemma-3-1b-it
Q4
1GB
52.57 tok/sEstimated
Auto-generated benchmark
LiquidAI/LFM2-1.2B
Q4
1GB
52.46 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen2.5-3B
Q4
2GB
51.86 tok/sEstimated
Auto-generated benchmark
nari-labs/Dia2-2B
Q4
2GB
51.39 tok/sEstimated
Auto-generated benchmark
google/embeddinggemma-300m
Q4
1GB
50.92 tok/sEstimated
Auto-generated benchmark
ibm-granite/granite-3.3-2b-instruct
Q4
1GB
49.97 tok/sEstimated
Auto-generated benchmark
google/gemma-2b
Q4
1GB
49.27 tok/sEstimated
Auto-generated benchmark
ibm-research/PowerMoE-3b
Q4
2GB
49.15 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-3B
Q4
2GB
49.03 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-Guard-3-1B
Q4
1GB
48.89 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen2.5-7B-Instruct
Q4
4GB
48.56 tok/sEstimated
Auto-generated benchmark
ibm-granite/granite-docling-258M
Q4
4GB
48.53 tok/sEstimated
Auto-generated benchmark
zai-org/GLM-4.5-Air
Q4
4GB
48.42 tok/sEstimated
Auto-generated benchmark
unsloth/Llama-3.2-1B-Instruct
Q4
1GB
48.33 tok/sEstimated
Auto-generated benchmark
openai-community/gpt2
Q4
4GB
48.29 tok/sEstimated
Auto-generated benchmark
bigscience/bloomz-560m
Q4
4GB
48.27 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen3-4B-Thinking-2507-FP8
Q4
2GB
48.24 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen3-0.6B
Q4
3GB
48.16 tok/sEstimated
Auto-generated benchmark
vikhyatk/moondream2
Q4
4GB
48.11 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen2.5-1.5B-Instruct
Q4
3GB
48.04 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen2.5-0.5B
Q4
3GB
48.01 tok/sEstimated
Auto-generated benchmark
black-forest-labs/FLUX.1-dev
Q4
4GB
47.99 tok/sEstimated
Auto-generated benchmark
lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-8bit
Q4
4GB
47.96 tok/sEstimated
Auto-generated benchmark
sshleifer/tiny-gpt2
Q4
4GB
47.95 tok/sEstimated
Auto-generated benchmark
ibm-granite/granite-3.3-8b-instruct
Q4
4GB
47.94 tok/sEstimated
Auto-generated benchmark
xgen-universe/Capybara
Q4
4GB
47.94 tok/sEstimated
Auto-generated benchmark
apple/OpenELM-1_1B-Instruct
Q4
1GB
47.94 tok/sEstimated
Auto-generated benchmark
inference-net/Schematron-3B
Q4
2GB
47.82 tok/sEstimated
Auto-generated benchmark
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Q4
3GB
47.60 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 (tight)
27.99 tok/sEstimated
7GB (have 8GB)
openai-community/gpt2FP16Not supported
15.51 tok/sEstimated
15GB (have 8GB)
Qwen/Qwen2.5-7B-InstructQ4Fits comfortably
48.56 tok/sEstimated
4GB (have 8GB)
Qwen/Qwen2.5-7B-InstructQ8Fits (tight)
32.84 tok/sEstimated
7GB (have 8GB)
Qwen/Qwen2.5-7B-InstructFP16Not supported
16.28 tok/sEstimated
15GB (have 8GB)
Qwen/Qwen3-0.6BQ4Fits comfortably
48.16 tok/sEstimated
3GB (have 8GB)
Qwen/Qwen3-0.6BQ8Fits comfortably
32.24 tok/sEstimated
6GB (have 8GB)
Qwen/Qwen3-0.6BFP16Not supported
17.61 tok/sEstimated
13GB (have 8GB)
Gensyn/Qwen2.5-0.5B-InstructQ4Fits comfortably
41.52 tok/sEstimated
3GB (have 8GB)
Gensyn/Qwen2.5-0.5B-InstructQ8Fits comfortably
29.92 tok/sEstimated
5GB (have 8GB)
Gensyn/Qwen2.5-0.5B-InstructFP16Not supported
17.34 tok/sEstimated
11GB (have 8GB)
meta-llama/Llama-3.1-8B-InstructQ4Fits comfortably
44.67 tok/sEstimated
4GB (have 8GB)
meta-llama/Llama-3.1-8B-InstructQ8Not supported
30.85 tok/sEstimated
9GB (have 8GB)
meta-llama/Llama-3.1-8B-InstructFP16Not supported
16.56 tok/sEstimated
17GB (have 8GB)
dphn/dolphin-2.9.1-yi-1.5-34bQ4Not supported
16.11 tok/sEstimated
17GB (have 8GB)
dphn/dolphin-2.9.1-yi-1.5-34bQ8Not supported
11.60 tok/sEstimated
35GB (have 8GB)
dphn/dolphin-2.9.1-yi-1.5-34bFP16Not supported
5.83 tok/sEstimated
70GB (have 8GB)
openai/gpt-oss-20bQ4Not supported
22.65 tok/sEstimated
10GB (have 8GB)
openai/gpt-oss-20bQ8Not supported
16.02 tok/sEstimated
20GB (have 8GB)
openai/gpt-oss-20bFP16Not supported
8.57 tok/sEstimated
41GB (have 8GB)
google/gemma-3-1b-itQ4Fits comfortably
52.57 tok/sEstimated
1GB (have 8GB)
google/gemma-3-1b-itQ8Fits comfortably
33.54 tok/sEstimated
1GB (have 8GB)
google/gemma-3-1b-itFP16Fits comfortably
19.98 tok/sEstimated
2GB (have 8GB)
Qwen/Qwen3-Embedding-0.6BQ4Fits comfortably
39.80 tok/sEstimated
3GB (have 8GB)
Qwen/Qwen3-Embedding-0.6BQ8Fits comfortably
33.49 tok/sEstimated
6GB (have 8GB)
Qwen/Qwen3-Embedding-0.6BFP16Not supported
16.05 tok/sEstimated
13GB (have 8GB)
Qwen/Qwen2.5-1.5B-InstructQ4Fits comfortably
48.04 tok/sEstimated
3GB (have 8GB)
Qwen/Qwen2.5-1.5B-InstructQ8Fits comfortably
33.53 tok/sEstimated
5GB (have 8GB)
Qwen/Qwen2.5-1.5B-InstructFP16Not supported
15.80 tok/sEstimated
11GB (have 8GB)
facebook/opt-125mQ4Fits comfortably
40.15 tok/sEstimated
4GB (have 8GB)
facebook/opt-125mQ8Fits (tight)
33.94 tok/sEstimated
7GB (have 8GB)
facebook/opt-125mFP16Not supported
17.60 tok/sEstimated
15GB (have 8GB)
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q4Fits comfortably
53.73 tok/sEstimated
1GB (have 8GB)
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q8Fits comfortably
36.71 tok/sEstimated
1GB (have 8GB)
TinyLlama/TinyLlama-1.1B-Chat-v1.0FP16Fits comfortably
18.21 tok/sEstimated
2GB (have 8GB)
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q4Fits comfortably
46.15 tok/sEstimated
4GB (have 8GB)
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q8Fits (tight)
33.35 tok/sEstimated
7GB (have 8GB)
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5FP16Not supported
16.99 tok/sEstimated
15GB (have 8GB)
Qwen/Qwen3-4B-Instruct-2507Q4Fits comfortably
45.97 tok/sEstimated
2GB (have 8GB)
Qwen/Qwen3-4B-Instruct-2507Q8Fits comfortably
29.61 tok/sEstimated
4GB (have 8GB)
Qwen/Qwen3-4B-Instruct-2507FP16Not supported
16.25 tok/sEstimated
9GB (have 8GB)
meta-llama/Llama-3.2-1B-InstructQ4Fits comfortably
57.97 tok/sEstimated
1GB (have 8GB)
meta-llama/Llama-3.2-1B-InstructQ8Fits comfortably
35.57 tok/sEstimated
1GB (have 8GB)
meta-llama/Llama-3.2-1B-InstructFP16Fits comfortably
22.09 tok/sEstimated
2GB (have 8GB)
openai/gpt-oss-120bQ4Not supported
8.59 tok/sEstimated
59GB (have 8GB)
openai/gpt-oss-120bQ8Not supported
6.52 tok/sEstimated
117GB (have 8GB)
openai/gpt-oss-120bFP16Not supported
3.69 tok/sEstimated
235GB (have 8GB)
Qwen/Qwen2.5-3B-InstructQ4Fits comfortably
56.27 tok/sEstimated
2GB (have 8GB)
Qwen/Qwen2.5-3B-InstructQ8Fits comfortably
35.62 tok/sEstimated
3GB (have 8GB)
openai-community/gpt2Q4Fits comfortably
48.29 tok/sEstimated
4GB (have 8GB)
openai-community/gpt2Q8
Fits (tight)7GB required · 8GB available
27.99 tok/sEstimated
openai-community/gpt2FP16
Not supported15GB required · 8GB available
15.51 tok/sEstimated
Qwen/Qwen2.5-7B-InstructQ4
Fits comfortably4GB required · 8GB available
48.56 tok/sEstimated
Qwen/Qwen2.5-7B-InstructQ8
Fits (tight)7GB required · 8GB available
32.84 tok/sEstimated
Qwen/Qwen2.5-7B-InstructFP16
Not supported15GB required · 8GB available
16.28 tok/sEstimated
Qwen/Qwen3-0.6BQ4
Fits comfortably3GB required · 8GB available
48.16 tok/sEstimated
Qwen/Qwen3-0.6BQ8
Fits comfortably6GB required · 8GB available
32.24 tok/sEstimated
Qwen/Qwen3-0.6BFP16
Not supported13GB required · 8GB available
17.61 tok/sEstimated
Gensyn/Qwen2.5-0.5B-InstructQ4
Fits comfortably3GB required · 8GB available
41.52 tok/sEstimated
Gensyn/Qwen2.5-0.5B-InstructQ8
Fits comfortably5GB required · 8GB available
29.92 tok/sEstimated
Gensyn/Qwen2.5-0.5B-InstructFP16
Not supported11GB required · 8GB available
17.34 tok/sEstimated
meta-llama/Llama-3.1-8B-InstructQ4
Fits comfortably4GB required · 8GB available
44.67 tok/sEstimated
meta-llama/Llama-3.1-8B-InstructQ8
Not supported9GB required · 8GB available
30.85 tok/sEstimated
meta-llama/Llama-3.1-8B-InstructFP16
Not supported17GB required · 8GB available
16.56 tok/sEstimated
dphn/dolphin-2.9.1-yi-1.5-34bQ4
Not supported17GB required · 8GB available
16.11 tok/sEstimated
dphn/dolphin-2.9.1-yi-1.5-34bQ8
Not supported35GB required · 8GB available
11.60 tok/sEstimated
dphn/dolphin-2.9.1-yi-1.5-34bFP16
Not supported70GB required · 8GB available
5.83 tok/sEstimated
openai/gpt-oss-20bQ4
Not supported10GB required · 8GB available
22.65 tok/sEstimated
openai/gpt-oss-20bQ8
Not supported20GB required · 8GB available
16.02 tok/sEstimated
openai/gpt-oss-20bFP16
Not supported41GB required · 8GB available
8.57 tok/sEstimated
google/gemma-3-1b-itQ4
Fits comfortably1GB required · 8GB available
52.57 tok/sEstimated
google/gemma-3-1b-itQ8
Fits comfortably1GB required · 8GB available
33.54 tok/sEstimated
google/gemma-3-1b-itFP16
Fits comfortably2GB required · 8GB available
19.98 tok/sEstimated
Qwen/Qwen3-Embedding-0.6BQ4
Fits comfortably3GB required · 8GB available
39.80 tok/sEstimated
Qwen/Qwen3-Embedding-0.6BQ8
Fits comfortably6GB required · 8GB available
33.49 tok/sEstimated
Qwen/Qwen3-Embedding-0.6BFP16
Not supported13GB required · 8GB available
16.05 tok/sEstimated
Qwen/Qwen2.5-1.5B-InstructQ4
Fits comfortably3GB required · 8GB available
48.04 tok/sEstimated
Qwen/Qwen2.5-1.5B-InstructQ8
Fits comfortably5GB required · 8GB available
33.53 tok/sEstimated
Qwen/Qwen2.5-1.5B-InstructFP16
Not supported11GB required · 8GB available
15.80 tok/sEstimated
facebook/opt-125mQ4
Fits comfortably4GB required · 8GB available
40.15 tok/sEstimated
facebook/opt-125mQ8
Fits (tight)7GB required · 8GB available
33.94 tok/sEstimated
facebook/opt-125mFP16
Not supported15GB required · 8GB available
17.60 tok/sEstimated
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q4
Fits comfortably1GB required · 8GB available
53.73 tok/sEstimated
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q8
Fits comfortably1GB required · 8GB available
36.71 tok/sEstimated
TinyLlama/TinyLlama-1.1B-Chat-v1.0FP16
Fits comfortably2GB required · 8GB available
18.21 tok/sEstimated
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q4
Fits comfortably4GB required · 8GB available
46.15 tok/sEstimated
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q8
Fits (tight)7GB required · 8GB available
33.35 tok/sEstimated
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5FP16
Not supported15GB required · 8GB available
16.99 tok/sEstimated
Qwen/Qwen3-4B-Instruct-2507Q4
Fits comfortably2GB required · 8GB available
45.97 tok/sEstimated
Qwen/Qwen3-4B-Instruct-2507Q8
Fits comfortably4GB required · 8GB available
29.61 tok/sEstimated
Qwen/Qwen3-4B-Instruct-2507FP16
Not supported9GB required · 8GB available
16.25 tok/sEstimated
meta-llama/Llama-3.2-1B-InstructQ4
Fits comfortably1GB required · 8GB available
57.97 tok/sEstimated
meta-llama/Llama-3.2-1B-InstructQ8
Fits comfortably1GB required · 8GB available
35.57 tok/sEstimated
meta-llama/Llama-3.2-1B-InstructFP16
Fits comfortably2GB required · 8GB available
22.09 tok/sEstimated
openai/gpt-oss-120bQ4
Not supported59GB required · 8GB available
8.59 tok/sEstimated
openai/gpt-oss-120bQ8
Not supported117GB required · 8GB available
6.52 tok/sEstimated
openai/gpt-oss-120bFP16
Not supported235GB required · 8GB available
3.69 tok/sEstimated
Qwen/Qwen2.5-3B-InstructQ4
Fits comfortably2GB required · 8GB available
56.27 tok/sEstimated
Qwen/Qwen2.5-3B-InstructQ8
Fits comfortably3GB required · 8GB available
35.62 tok/sEstimated
openai-community/gpt2Q4
Fits comfortably4GB required · 8GB available
48.29 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

Starfield
8GB VRAM

RPG • 2023

Elden Ring
8GB VRAM

Action RPG • 2022

Red Dead Redemption 2
8GB VRAM

Action Adventure • 2019

Grand Theft Auto V
4GB VRAM

Action Adventure • 2015

The Witcher 3: Wild Hunt
6GB VRAM

RPG • 2015

Forza Horizon 5
8GB VRAM

Racing • 2021

Assassin's Creed Mirage
8GB VRAM

Action Adventure • 2023

Assassin's Creed Valhalla
8GB VRAM

Action RPG • 2020

Path of Exile 2
8GB VRAM

Action RPG • 2024

Diablo IV
8GB VRAM

Action RPG • 2023

View all 41 compatible games