Radeon PRO V710

The Radeon PRO V710 is an Amd GPU built on the RDNA 3.0 architecture, released 2024-10-03. For running AI locally, the numbers that matter are its 28 GB of GDDR6 and 504 GB/s of memory bandwidth. VRAM decides which models fit at all; bandwidth sets how fast they generate text.

What you can run on 28 GB

At Q4_K_M quantization (the usual local default), 28 GB holds models up to roughly 44B parameters, leaving headroom for context. On this card you can run, among others:

• G9v3-39A5B - 39B parameters
• K2 Horizon MoVA 36B A4B - 37.4B parameters
• Ornith-1.5-35B-A3B - 36B parameters
• Qwen3.5 35B A3B - 36B parameters
• Qwen3.6 35B A3B - 36B parameters

Larger models need a higher-VRAM card, a second GPU, or CPU offload (which is much slower). Check any specific model with the VRAM calculator, or see the full picture on what can I run.

Local LLM speed (LLaMA 3, llama.cpp)

Single-stream token-generation throughput - estimated from memory bandwidth:

Model (quant)	Speed on Radeon PRO V710
Llama 3 8B (Q4_K_M)	59 tok/s
Llama 3 8B (F16)	26.8 tok/s
Llama 3 70B (Q4_K_M)	✗ won't fit

Because decode is memory-bandwidth bound, the 504 GB/s figure is the best single predictor of chat speed on this card. Estimates are calibrated against measured RTX-40-series cards and are typically within ~15%.

Memory and power

• VRAM: 28 GB GDDR6 (224-bit bus)
• Bandwidth: 504 GB/s
• TDP: 158 W - a 450 W+ power supply is recommended
• Process: 5 nm
• Interface: PCIe 4.0 x16

Quantization and context

Quantization trades a little quality for a lot of VRAM. On 28 GB you can fit roughly a 44B model at Q4_K_M, about a 24B model at the higher-quality Q8, or a smaller model at full FP16. Longer context windows also consume VRAM (the KV cache grows with context length), so leave a few GB of headroom if you plan to use large prompts or many concurrent requests. For most chat and coding use, Q4_K_M on this card is the sweet spot between speed, quality, and the 28 GB budget.

How it compares

Similar cards for local AI, by VRAM and 8B-Q4 speed:

GPU	VRAM	Bandwidth	Llama 3 8B Q4
Radeon PRO V710	28 GB	504 GB/s	59 tok/s
AMD Radeon RX 7900 XTX	24 GB	960 GB/s	112.3 tok/s
Arc Pro B60	24 GB	456 GB/s	53.4 tok/s
NVIDIA RTX 5000 Ada Generation	32 GB	768 GB/s	89.9 tok/s

Bottom line

The Radeon PRO V710 is best for llm-inference, image-gen, comfyui. With 24 GB+ it comfortably handles most open models, including 30B-class at Q4. If you need more, compare with AMD Radeon RX 7900 XTX and Arc Pro B60.

Sources

• Specifications: RightNow GPU Database (TechPowerUp data)
• Benchmarks: GPU-Benchmarks-on-LLM-Inference (basis for the bandwidth estimate)

Specs and benchmarks last checked 2026-10-30. Verify current pricing before buying.