Minimum VRAM
180GB
FP16 (full model) • Q4 option ≈ 45GB
Best Performance
AMD Instinct MI300X
~58 tok/s • FP16
Most Affordable
Apple M2 Ultra
FP16 • ~8 tok/s • From $5,999
Quick answer: Redhatai Llama 3.2 90B Vision Instruct FP8 Dynamic needs roughly 45GB VRAM for Q4_K_M and 68GB for Q5_K_M. Use Q8 (90GB) or FP16 (180GB) for higher quality output.
Full-model (FP16) requirements are shown by default. Quantized builds like Q4 trade accuracy for lower VRAM usage.
Filter by quantization, price, and VRAM to compare performance estimates.
Showing FP16 compatibility. Switch tabs to explore other quantizations.
| GPU | Speed | VRAM Requirement | Typical price |
|---|---|---|---|
AMD Instinct MI300XEstimated AMD | ~58 tok/s FP16 | 180GB VRAM used192GB total on card | $15,000View GPU → |
NVIDIA H200 SXM 141GBEstimated NVIDIA | ~52 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used141GB total on card | $35,000View GPU → |
NVIDIA H100 SXM5 80GBEstimated NVIDIA | ~38 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used80GB total on card | $30,000View GPU → |
AMD Instinct MI250XEstimated AMD | ~36 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used128GB total on card | $11,000View GPU → |
NVIDIA H100 PCIe 80GBEstimated NVIDIA | ~24 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used80GB total on card | $25,000View GPU → |
RTX 5090Data coming soon NVIDIA | ~23 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used32GB total on card | $1,999View GPU → |
NVIDIA A100 80GB SXM4Estimated NVIDIA | ~22 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used80GB total on card | $11,000View GPU → |
AMD Instinct MI210Estimated AMD | ~18 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used64GB total on card | $6,000View GPU → |
NVIDIA A100 40GB PCIeData coming soon NVIDIA | ~17 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used40GB total on card | $9,000View GPU → |
RTX 4090Data coming soon NVIDIA | ~14 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used24GB total on card | $1,599View GPU → |
NVIDIA RTX 6000 AdaEstimated NVIDIA | ~14 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used48GB total on card | $6,999View GPU → |
NVIDIA L40Estimated NVIDIA | ~13 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used48GB total on card | $7,999View GPU → |
NVIDIA L40SEstimated NVIDIA | ~13 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used48GB total on card | $10,000View GPU → |
RTX 5080Data coming soon NVIDIA | ~12 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $1,199View GPU → |
RTX 3090Data coming soon NVIDIA | ~12 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used24GB total on card | $1,499View GPU → |
AMD Radeon Pro W7900Estimated AMD | ~11 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used48GB total on card | $3,999View GPU → |
RX 7900 XTXData coming soon AMD | ~11 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used24GB total on card | $999View GPU → |
RTX 5070 TiData coming soon NVIDIA | ~11 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $799View GPU → |
NVIDIA A6000Estimated NVIDIA | ~10 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used48GB total on card | $4,699View GPU → |
RTX 4080 SuperData coming soon NVIDIA | ~10 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $999View GPU → |
RTX 3080Data coming soon NVIDIA | ~10 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used10GB total on card | $699View GPU → |
NVIDIA A5000Data coming soon NVIDIA | ~10 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used24GB total on card | $2,399View GPU → |
RTX 4080Data coming soon NVIDIA | ~9 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $1,199View GPU → |
RX 7900 XTData coming soon AMD | ~9 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used20GB total on card | $899View GPU → |
RTX 4070 Ti SuperData coming soon NVIDIA | ~9 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $799View GPU → |
RTX 5070Data coming soon NVIDIA | ~8 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used12GB total on card | $599View GPU → |
Apple M2 UltraEstimated Apple | ~8 tok/s FP16 | 180GB VRAM used192GB total on card | $5,999View GPU → |
RX 9070 XTData coming soon AMD | ~7 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $599View GPU → |
RX 7800 XTData coming soon AMD | ~7 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $499View GPU → |
RX 7900 GREData coming soon AMD | ~7 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $649View GPU → |
AMD Radeon Pro W7800Data coming soon AMD | ~7 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used32GB total on card | $2,499View GPU → |
RTX 4070 TiData coming soon NVIDIA | ~7 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used12GB total on card | $799View GPU → |
RTX 4070 SuperData coming soon NVIDIA | ~7 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used12GB total on card | $599View GPU → |
RX 9070Data coming soon AMD | ~7 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $499View GPU → |
Intel Arc A770 16GBData coming soon Intel | ~7 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $349View GPU → |
RTX 4070Data coming soon NVIDIA | ~6 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used12GB total on card | $599View GPU → |
RX 6900 XTData coming soon AMD | ~6 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $999View GPU → |
RX 6800 XTData coming soon AMD | ~6 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $649View GPU → |
Intel Arc A750Data coming soon Intel | ~6 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used8GB total on card | $289View GPU → |
NVIDIA A4000Data coming soon NVIDIA | ~6 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $999View GPU → |
RTX 3070Data coming soon NVIDIA | ~6 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used8GB total on card | $499View GPU → |
Intel Arc B580Data coming soon Intel | ~6 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used12GB total on card | $249View GPU → |
Apple M4 MaxEstimated Apple | ~6 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used128GB total on card | $3,999View GPU → |
RX 7700 XTData coming soon AMD | ~5 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used12GB total on card | $449View GPU → |
Intel Arc B570Data coming soon Intel | ~5 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used10GB total on card | $219View GPU → |
Intel Arc Pro A60Data coming soon Intel | ~5 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used12GB total on card | $599View GPU → |
NVIDIA L4Data coming soon NVIDIA | ~5 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used24GB total on card | $5,000View GPU → |
RTX 3060 12GBData coming soon NVIDIA | ~4 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used12GB total on card | $329View GPU → |
Apple M3 MaxEstimated Apple | ~4 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used128GB total on card | $3,999View GPU → |
Apple M2 MaxEstimated Apple | ~4 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used96GB total on card | $3,199View GPU → |
RTX 4060 Ti 16GBData coming soon NVIDIA | ~4 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $499View GPU → |
RTX 4060 Ti 8GBData coming soon NVIDIA | ~4 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used8GB total on card | $399View GPU → |
RTX 4060Data coming soon NVIDIA | ~3 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used8GB total on card | $299View GPU → |
RX 7600 XTData coming soon AMD | ~3 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used16GB total on card | $329View GPU → |
RX 7600Data coming soon AMD | ~3 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used8GB total on card | $269View GPU → |
Intel Arc Pro A40Data coming soon Intel | ~3 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used6GB total on card | $399View GPU → |
Apple M4 ProEstimated Apple | ~3 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used64GB total on card | $1,999View GPU → |
AMD Ryzen AI Max+ 395Estimated AMD | ~3 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used128GB total on card | EnterpriseView GPU → |
AMD Ryzen AI Max 385Estimated AMD | ~3 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used128GB total on card | EnterpriseView GPU → |
AMD Ryzen AI Max Pro 385Estimated AMD | ~3 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used128GB total on card | EnterpriseView GPU → |
Apple M2 ProData coming soon Apple | ~2 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used32GB total on card | $1,999View GPU → |
Apple M3 ProData coming soon Apple | ~2 tok/s FP16⚠ Insufficient VRAM | 180GB VRAM used36GB total on card | $1,999View GPU → |
Redhatai Llama 3.2 90B Vision Instruct FP8 Dynamic 90B parametre içerir ve 45GB VRAM gerektirir - choose the best GPU for your needs
For Better Performance
Run Redhatai Llama 3.2 90B Vision Instruct FP8 Dynamic faster with AMD Instinct MI300X. For just $130 more, significantly boost your tokens/sec performance.
Hardware requirements and model sizes at a glance.
| Component | Minimum | Recommended | Optimal |
|---|---|---|---|
| VRAM | 45GB (Q4) | 90GB (Q8) | 180GB (FP16) |
| RAM | 68GB | 135GB | 225GB |
| Disk | 36GB | 72GB | - |
| Model size | 45GB (Q4) | 90GB (Q8) | 180GB (FP16) |
| CPU | Modern CPU (Ryzen 5/Intel i5 or better) | Modern CPU (Ryzen 5/Intel i5 or better) | Modern CPU (Ryzen 5/Intel i5 or better) |
Note: Performance estimates are calculated. Real results may vary. Methodology · Submit real data
Common questions about running Redhatai Llama 3.2 90B Vision Instruct FP8 Dynamic locally
This model delivers strong local performance when paired with modern GPUs. Use the hardware guidance below to choose the right quantization tier for your build.
Use runtimes like llama.cpp, text-generation-webui, or vLLM. Download the quantized weights from Hugging Face, ensure you have enough VRAM for your target quantization, and launch with GPU acceleration (CUDA/ROCm/Metal).
Start with Q4 for wide GPU compatibility. Upgrade to Q8 if you have spare VRAM and want extra quality. FP16 delivers the highest fidelity but demands workstation or multi-GPU setups.
Q4_K_M and Q5_K_M are GGUF quantization formats that balance quality and VRAM usage. Q4_K_M uses about 45GB VRAM. Q5_K_M uses about 68GB VRAM and keeps more accuracy. Q8 (~90GB) offers near-FP16 quality. Standard Q4 is the most memory-efficient option for Redhatai Llama 3.2 90B Vision Instruct FP8 Dynamic.
Official weights are available via Hugging Face. Quantized builds (Q4, Q8) can be loaded into runtimes like llama.cpp, text-generation-webui, or vLLM. Always verify the publisher before downloading.
See how Redhatai Llama 3.2 90B Vision Instruct FP8 Dynamic compares to other popular models.