AMD Radeon AI Pro 9700 32GB
The AMD Radeon AI Pro 9700 32GB has 32 GB VRAM and 640 GB/s memory bandwidth. It can run 45 of our 81 tracked models natively in VRAM at 8k context.
With 32 GB GDDR6, the AMD Radeon AI Pro 9700 32GB is a datacenter-tier GPU that can run 45 models natively. It handles 70B-class models at Q4 quantization.
The AMD Radeon AI Pro 9700 is a professional AI accelerator built on RDNA 4 with 32GB of GDDR6 memory and 640 GB/s bandwidth. Featuring 4,096 stream processors and 128 AI Accelerators on the Navi 48 die, it delivers 47.8 TFLOPS of FP32 and 95.7 TFLOPS of FP16 performance. Designed for local AI inference and development workloads, it offers a competitive professional option for single-GPU inference deployments where ECC memory and datacenter infrastructure aren't required.
AMD Radeon AI Pro 9700 32GB: 2025 RDNA 4 professional AI accelerator on the Navi 48 die — 32GB GDDR6 at 640 GB/s, 4,096 stream processors, 128 AI Accelerators; 47.8 TFLOPS FP32 / 95.7 TFLOPS FP16.
34B models fit at Q4_K_M entirely in VRAM, similar to the Radeon PRO W7800's capacity tier. ~18-26 t/s for 7B Q4.
ROCm on Linux; Vulkan backend on Windows. Targets single-GPU inference and development workloads where ECC memory and full datacenter infrastructure aren't required — a lower-cost alternative to the W7800/W7900 for local AI work.
| Vendor | AMD |
| Architecture | RDNA 4 |
| VRAM | 32 GB |
| Memory type | GDDR6 |
| Memory bandwidth | 640 GB/s |
| Compute backend | ROCM |
| Tier | Datacenter |
| Released | 2025 |
| Models (native) | 45 / 81 |
| Models (offload) | 10 / 81 |
Popular models for this GPU
Models this GPU runs natively in VRAM (45)
- Mixtral 8x7B Instruct v0.146.7B · MMLU-Pro 29.7Q3_K_M · ~19.1 t/s
- Command-R 35B35B · MMLU-Pro 33.0Q2_K · ~17.3 t/s
- Qwen 3.5 35B-A3B (MoE)35B · MMLU-Pro 85.3Q5_K_M · ~57.1 t/s
- Qwen 3.6 35B35B · MMLU-Pro 85.2Q5_K_M · ~15.4 t/s
- Yi 1.5 34B Chat34.4B · MMLU-Pro 37.0Q5_K_M · ~15.7 t/s
Show 40 more
- Qwen3 32B32.8B · MMLU-Pro 65.5Q5_K_M · ~16.8 t/s
- Qwen 2.5 32B Instruct32.5B · MMLU-Pro 69.0Q5_K_M · ~16.5 t/s
- Qwen 2.5 Coder 32B Instruct32.5B · MMLU-Pro 50.4Q5_K_M · ~16.5 t/s
- DeepSeek R1 Distill Qwen 32B32.5B · MMLU-Pro 65.0Q5_K_M · ~16.5 t/s
- Nemotron 3 Nano 30B32B · MMLU-Pro 78.3Q6_K · ~48.1 t/s
- Gemma 4 31B31B · MMLU-Pro 85.2Q5_K_M · ~16.4 t/s
- Qwen3 30B-A3B (MoE)30B · MMLU-Pro 61.5Q6_K · ~46.1 t/s
- Gemma 2 27B Instruct27.2B · MMLU-Pro 38.0Q6_K · ~16.4 t/s
- Gemma 3 27B Instruct27B · MMLU-Pro 67.5Q6_K · ~17.5 t/s
- Qwen 3.6 27B27B · MMLU-Pro 86.2Q6_K · ~18.3 t/s
- Bonsai 27B27B · MMLU-Pro 81.5Ternary (Q2_0) · ~47.2 t/s
- Gemma 4 26B (MoE)26B · MMLU-Pro 82.6Q6_K · ~38.6 t/s
- Mistral Small 3.1 24B Instruct24B · MMLU-Pro 66.8Q8_0 · ~15.5 t/s
- Mistral Small 22B22.2B · MMLU-Pro 49.2Q8_0 · ~16.3 t/s
- GPT-OSS 20B21B · MMLU-Pro 67.9Q8_0 · ~28.5 t/s
- Qwen3 14B14.8B · MMLU-Pro 61.0Q8_0 · ~24.4 t/s
- Qwen 2.5 14B Instruct14.7B · MMLU-Pro 63.7Q8_0 · ~24.1 t/s
- Phi-4 14B Instruct14B · MMLU-Pro 70.4Q8_0 · ~25.6 t/s
- Mistral Nemo 12B Instruct12.2B · MMLU-Pro 35.6BF16 · ~16.2 t/s
- Gemma 3 12B Instruct12.2B · MMLU-Pro 60.6BF16 · ~16.3 t/s
- Gemma 4 12B (Unified)12B · MMLU-Pro 77.2Q8_0 · ~26 t/s
- Gemma 2 9B Instruct9.2B · MMLU-Pro 32.0BF16 · ~19.6 t/s
- Llama 3.1 8B Instruct8B · MMLU-Pro 48.3BF16 · ~24.4 t/s
- DeepSeek R1 Distill Llama 8B8B · MMLU-Pro 41.0BF16 · ~24.4 t/s
- Qwen3 8B8B · MMLU-Pro 56.7BF16 · ~24.2 t/s
- Qwen 2.5 7B Instruct7.6B · MMLU-Pro 56.3BF16 · ~26.5 t/s
- Mistral 7B Instruct v0.37.25B · MMLU-Pro 30.0BF16 · ~26.7 t/s
- Gemma 3 4B Instruct4B · MMLU-Pro 43.6FP32 · ~25.2 t/s
- Gemma 4 E4B4B · MMLU-Pro 69.4FP32 · ~24.5 t/s
- Phi-3.5 Mini Instruct3.8B · MMLU-Pro 47.4FP32 · ~22.6 t/s
- Llama 3.2 3B Instruct3.2B · MMLU-Pro 24.0FP32 · ~30.3 t/s
- Qwen 2.5 3B Instruct3.1B · MMLU-Pro 32.4FP32 · ~32.8 t/s
- Gemma 2 2B Instruct2.6B · MMLU-Pro 17.8FP32 · ~36.9 t/s
- Gemma 4 E2B2B · MMLU-Pro 60.0FP32 · ~49.5 t/s
- SmolLM2 1.7B Instruct1.7B · MMLU-Pro 19.0FP32 · ~49.5 t/s
- Qwen 2.5 1.5B Instruct1.5B · MMLU-Pro 16.8FP32 · ~66.7 t/s
- Llama 3.2 1B Instruct1.24B · MMLU-Pro 12.5FP32 · ~79.6 t/s
- Gemma 3 1B Instruct1B · MMLU-Pro 14.7FP32 · ~96.1 t/s
- Qwen 2.5 0.5B Instruct0.5B · MMLU-Pro 10.0FP32 · ~198 t/s
- SmolLM2 360M Instruct0.36B · MMLU-Pro 8.0FP32 · ~234.3 t/s
Models that fit with CPU offload (10)
These use system RAM for layers that don't fit in VRAM — expect much slower inference.
- Qwen 3.5 122B-A10B (MoE)122B · MMLU-Pro 86.7Q2_K · ~4.1 t/s
- Nemotron 3 Super 120B120B · MMLU-Pro 83.7Q2_K · ~4.1 t/s
- GPT-OSS 120B117B · MMLU-Pro 80.7Q2_K · ~9.8 t/s
- Llama 4 Scout 109B109B · MMLU-Pro 74.3Q2_K · ~2.9 t/s
- GLM-4.5 Air 106B106B · MMLU-Pro 81.4Q2_K · ~4.7 t/s
- GLM-4.6V 106B106B · MMLU-Pro 79.9Q2_K · ~4.7 t/s
- Qwen 2.5 72B Instruct72B · MMLU-Pro 71.1Q4_K_M · ~1.4 t/s
- Llama 3.3 70B Instruct70B · MMLU-Pro 68.9Q4_K_M · ~1.5 t/s
- DeepSeek R1 Distill Llama 70B70B · MMLU-Pro 70.0Q4_K_M · ~1.5 t/s
- Llama 3.1 70B Instruct70B · MMLU-Pro 66.4Q4_K_M · ~1.5 t/s
Too large for this GPU (26)
- Mixtral 8x22B Instruct v0.1
- Llama 3.1 405B Instruct
- DeepSeek V3 671B
- DeepSeek R1 671B
- Llama 4 Maverick 400B
- Qwen3 235B-A22B (MoE)
- MiniMax M1 456B
- GLM-4.5 355B
- GLM-4.6 355B
- GLM-4.7 358B
- MiniMax M2.5 229B
- GLM-5 744B
- MiniMax M2.7 229B
- Kimi K2.6
- GLM-5.1 754B
- DeepSeek V4 Pro 1.6T
- DeepSeek V4 Flash 284B
- GLM-5.2 753B
- Nemotron 3 Ultra 550B-A55B
- Step 3.5 Flash
- Step 3.7 Flash
- MiMo V2.5 Pro
- Kimi K2.5
- MiniMax M3
- Inkling
- Kimi K3
Compare AMD Radeon AI Pro 9700 32GB with other GPUs
Frequently asked questions
- How much VRAM does the AMD Radeon AI Pro 9700 32GB have?
- The AMD Radeon AI Pro 9700 32GB has 32 GB of GDDR6 with 640 GB/s memory bandwidth.
- What is the AMD Radeon AI Pro 9700 32GB best for?
- With 32 GB of VRAM, the AMD Radeon AI Pro 9700 32GB is well-suited for running 7B–32B models at Q4 with room for context, making it a great all-rounder for local LLM inference.
- What LLMs can the AMD Radeon AI Pro 9700 32GB run locally?
- The AMD Radeon AI Pro 9700 32GB can run 45 of the 81 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at BF16, Llama 3.2 3B Instruct at FP32, Llama 3.2 1B Instruct at FP32.
- Can the AMD Radeon AI Pro 9700 32GB run Llama 3.3 70B Instruct?
- The AMD Radeon AI Pro 9700 32GB can run Llama 3.3 70B Instruct with CPU offload at Q4_K_M quantization, but inference will be slower than native VRAM execution.
- Can the AMD Radeon AI Pro 9700 32GB run Qwen 3.6 27B?
- Yes. The AMD Radeon AI Pro 9700 32GB runs Qwen 3.6 27B natively in VRAM at Q6_K quantization, achieving approximately 18.3 tokens per second.
- Can the AMD Radeon AI Pro 9700 32GB run Llama 3.1 8B Instruct?
- Yes. The AMD Radeon AI Pro 9700 32GB runs Llama 3.1 8B Instruct natively in VRAM at BF16 quantization, achieving approximately 24.4 tokens per second.
- Can I rent the AMD Radeon AI Pro 9700 32GB instead of buying it?
- Yes — RunPod and similar cloud GPU providers let you rent AMD Radeon AI Pro 9700 32GB instances by the hour, with no long-term contract. This is often cheaper than buying if you only need it occasionally, and lets you try the GPU before committing to a purchase.