AMD MI300X - 192GB usable
Specifications
| Brand | AMD |
|---|---|
| Model | MI300X |
| Usable VRAM | 192GB |
| Architecture | CDNA3 |
| CUDA / Stream Processors | 14,592 |
| Memory Bandwidth | 5300 GB/s |
| TDP | 750W |
| FP32 TFLOPS | 163 |
Current Offers
Used from $19000
Prices last updated:
GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.
Price History
- eBay$19000at low
For AI / LLM Use
Best for running 70B+ models on a single GPU. Very fast generation speed. Datacenter card with no display output, may need aftermarket cooling.
What Models Can It Run?
- 70B full precision
- 70B Q4_K_M, 30B full precision
- 30B Q6_K, 70B Q2_K
- 30B Q4_K_M, 14B full precision, 70B Q2 (tight)
- 14B Q6_K, 30B Q3_K (tight)
- 14B Q4_K_M, 7B full precision
- 7B Q6_K, 14B Q3_K (tight)
- 7B Q4_K_M only
Estimated Performance
Generation: ~398 tokens/sec
Prefill: ~2911 tokens/sec
Recommended Quantisations
- Q6_K or Q8 for best quality
- Q4_K_M for larger models
- Full precision for 30B and below
Pros & Cons
Pros
- 192GB usable VRAM: handles large models
- High memory bandwidth for fast generation
- CDNA3 architecture: supported by current ROCm stacks
Cons
- 750W TDP: high power draw
- ROCm and CUDA-first framework compatibility should be checked before purchase
- No display output: headless only
- May need aftermarket cooling solution
Community Verdict
No community reviews yet for the MI300X. Know a good review? Let us know.