AMD
Operating mode
Use this to bias workload recommendations toward responsiveness, background autonomy, lighter serving, or multi-GPU scale-out.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
The AMD Instinct MI210 64GB is a CDNA 2 datacenter GPU and AMD's PCIe-based alternative to the OAM-form-factor MI250X. It offers 64 GB of HBM2e with 1.6 TB/s of memory bandwidth and full ROCm support. It was designed for AI training and inference in data centers and is particularly competitive for its HBM2e capacity, enabling 70B Q4 inference in a single PCIe card without requiring specialized server infrastructure.
Beyond LLMs
What AI tasks this GPU can handle — from text generation to image and video creation.
| Capability | Status | Representative Model |
|---|---|---|
| LLM Chat (7B) | Runs natively | Llama 3.1 8B Q4 |
| LLM Coding (30B) | Runs natively | Qwen 3 30B Q4 |
| LLM Large (70B) | Runs natively | Llama 3.1 70B Q4 |
| Image Gen (SDXL) | Runs natively | SDXL 1.0 FP16 |
| Image Gen (Flux) | Runs natively | Flux.1 Dev FP16 |
| Image Gen (SD 3.5) | Runs natively | SD 3.5 Large FP16 |
| Video Short (25f) | Runs natively | LTX Video 2B |
| Video Long (100f) | Very constrained | Wan Video 14B |
Architecture
CDNA 2 powers the Instinct MI210 and MI250/MI250X accelerators. It introduced multi-die packaging with up to 128 GB HBM2e and Infinity Fabric for die-to-die communication.
AI Relevance
With up to 128 GB HBM2e memory and strong ROCm support, CDNA 2 GPUs can host large language models. The MI250X was used in the Frontier exascale supercomputer and supports major AI frameworks.
Conselho de compra
Excelente escolha para IA local
Roda 29 de 50 modelos principais bem — um ótimo coringa para inferência local.
64.0 GB
VRAM
$10,000
Preço sugerido
$156/GB
Custo por GB de VRAM
Melhores modelos para esta GPU
What will limit you first
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best upgrade itinerary
Unlocks 1 additional models that do not fit on the current setup.
Quer mais margem? Mac Studio M3 Ultra 96GB (96.0 GB unified memory) é o próximo passo.
Chat
SQwen 3.5 27B matches Chat and keeps a practical fit profile. It is a recent-generation family, which helps on current local SOTA workloads. It fits natively with comfortable headroom. Context coverage stays within the requested workload envelope. Known distribution channels: huggingface, ollama, lm-studio.
Coding
SQwen3-Coder-Next is a specialized fit for Coding. It is a recent-generation family, which helps on current local SOTA workloads. It should run, but memory headroom will be limited. Context coverage stays within the requested workload envelope. Known distribution channels: huggingface, ollama, lm-studio.
Agentic Coding
SQwen3-Coder-Next is a specialized fit for Agentic Coding. It is a recent-generation family, which helps on current local SOTA workloads. It should run, but memory headroom will be limited. Context coverage stays within the requested workload envelope. Known distribution channels: huggingface, ollama, lm-studio.
Reasoning
SQwen 3.5 27B matches Reasoning and keeps a practical fit profile. It is a recent-generation family, which helps on current local SOTA workloads. It fits natively with comfortable headroom. Context coverage stays within the requested workload envelope. Known distribution channels: huggingface, ollama, lm-studio.
RAG
SQwen 3.5 27B matches RAG and keeps a practical fit profile. It is a recent-generation family, which helps on current local SOTA workloads. It fits natively with comfortable headroom. Context coverage stays within the requested workload envelope. Known distribution channels: huggingface, ollama, lm-studio.
Qwen 3.6 35B A3BQwen3-Coder 30B A3B InstructQwen 3.5 35B A3BQwen3-VL 30B A3B InstructQwen3-Coder-NextQwen 3.5 27BQwen 3 32BQwen 3 30B A3B
Magistral Small 2507Devstral Small 2 24B InstructQwen 2.5 VL 72BQwen 3.6 27B
Nemotron 3 Nano 30B
Gemma 4 31BDevstral Small 1.1Nemotron Cascade 2 30B A3BQwen 3 14BQwen 3.5 9B
Phi-4-reasoning-plus 14B
GPT-OSS 20BQwen 3 8B
EXAONE 4.0 32BGemma 4 26B A4BQwen 3.5 4BMinistral 3 14BNemotron Nano 8BPhi-4 Mini Reasoning 4B
Jina Embeddings v3
BGE M3Qwen 3.5 397B A17BDevstral 2 123B Instruct
Kimi K2.5Kimi K2.6
DeepSeek V4 ProQwen 3.5 122B A10BDeepSeek V4 FlashMistral Small 4 119B
Command A 111BGPT-OSS 120B
GLM-5.1Pixtral Large 124BGLM-5DeepSeek V3.2Qwen 3 235B A22BQwen3-Coder 480B A35B InstructLeanstral 119B A6BDeepSeek Coder V2 236BDeepSeek R1 671BDeepSeek V3.1 671BQuase ao alcance
Modelos de alta qualidade que precisam de um pouco mais de memória
Image & Video Generation
51 of 52 models can generate images or video on your AMD Instinct MI210 64GB
| Model | Max Resolution | Gen Time | Grade |
|---|---|---|---|
| SD TurboImage | 512×512 | 300ms | S |
| Stable Diffusion 1.5Image | 512×768 | 500ms | S |
| Realistic Vision v5.1Image | 512×768 | 500ms | S |
| DreamShaper 8Image | 512×768 | 500ms | S |
| LCM DreamShaper v7Image | 512×768 | 200ms | S |
| PixArt-SigmaImage | 1024×1024 | ~2s | S |
| FramePack I2VVideo | 1280×720 | ~3.7s/frame | S |
| SDXL TurboImage | 512×512 | 300ms | S |
| SDXL LightningImage | 1024×1024 | 800ms | S |
| Stable Diffusion XL 1.0Image | 1024×1024 | ~2s | S |
| Playground v2.5Image | 1024×1024 | ~3s | S |
| RealVisXL v5.0Image | 1024×1024 | ~2.3s | S |
| DreamShaper XLImage | 1024×1024 | ~2.3s | S |
| Juggernaut XL v9Image | 1024×1024 | ~2.3s | S |
| Animagine XL 3.1Image | 1024×1024 | ~2.3s | S |
| Pony Diffusion V6 XLImage | 1024×1024 | ~2.3s | S |
| Animagine XL 4.0Image | 1024×1024 | ~2.3s | S |
| Illustrious XLImage | 1024×1024 | ~2.3s | S |
| Wan Video 2.1 1.3BVideo | 480×832 | ~1.5s/frame | S |
| Stable Diffusion 3.5 MediumImage | 1024×1024 | ~3.5s | S |
| Flux.2 Klein 4BImage | 1024×1024 | 600ms | S |
| LTX Video 2BVideo | 1280×720 | ~1.8s/frame | S |
| KolorsImage | 1024×1024 | ~4.1s | S |
| Stable CascadeImage | 1024×1024 | ~5.1s | S |
| AuraFlow v0.3Image | 1536×1536 | ~9.1s | S |
| Stable Diffusion 3.5 LargeImage | 1024×1024 | ~11.1s | S |
| Stable Diffusion 3.5 Large TurboImage | 1024×1024 | ~2s | S |
| CogVideoX 2BVideo | 720×480 | ~1.8s/frame | S |
| HunyuanVideoVideo | 720×1280 | ~3.7s/frame | S |
| ChromaImage | 1024×1024 | ~2s | S |
| Z-Image TurboImage | 1536×1536 | ~2.1s | S |
| Flux.1 DevImage | 1024×1024 | ~9.1s | S |
| Flux.1 SchnellImage | 1024×1024 | ~1.8s | S |
| LTX Video 13BVideo | 1280×720 | ~3.7s/frame | S |
| Flux.1 Kontext DevImage | 1024×1024 | ~10.1s | S |
| AnimateDiff v1.5.3Video | 512×768 | 900ms/frame | S |
| Cosmos Diffusion 7BVideo | 1024×576 | ~2.9s/frame | S |
| CogVideoX 5BVideo | 720×480 | ~2.5s/frame | S |
| Wan2.2 TI2V 5BVideo | 832×480 | ~2.5s/frame | S |
| Flux.2 Klein 9BImage | 1024×1024 | ~1s | S |
| Flux.1 Fill DevImage | 1024×1024 | ~8.6s | S |
| Mochi 1 PreviewVideo | 848×480 | ~3.3s/frame | S |
| HunyuanVideo 1.5Video | 720×1280 | ~3.1s/frame | S |
| Helios 14BVideo | 1280×720 | ~3.8s/frame | S |
| SkyReels V2 14BVideo | 1280×720 | ~3.8s/frame | S |
| Wan Video 2.1 14BVideo | 480×832 | ~3.8s/frame | A |
| Wan Video 2.2 14BVideo | 480×832 | ~3.8s/frame | A |
| Qwen ImageImage | 1024×1024 | ~3.4s | B |
| Qwen Image EditImage | 1024×1024 | ~3.4s | B |
| Flux.2 DevImage | 256×256 | ~1m 36s | B |
| MAGI-1Video | 256×256 | ~7.7s/frame | B |
| HunyuanImage 3.0Image | 256×256 | ~6s | F |
Image models estimated at 1024×1024 (28 steps, FP16). Video models estimated at 768×512 (25 frames, 30 steps, FP16). Actual performance varies with runtime and system load.
Upgrade paths
See what you unlock with more powerful hardware
Opções de upgrade
Unlocks 1 additional models that do not fit on the current setup.
~$3,999 MSRP
Unlocks 8 additional models that do not fit on the current setup.
~$2,499 MSRP
Unlocks 8 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 59%.
~$12,000 MSRP
Unlocks 21 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 88%.
~$8,000 MSRP
AMD Instinct MI210 64GB (64 GB VRAM) can run these top models: Qwen 3.6 35B A3B (score: 95/100), Qwen3-Coder 30B A3B Instruct (score: 94/100), Qwen 3.5 35B A3B (score: 94/100). See the full compatibility list above.
AMD Instinct MI210 64GB has 64 GB of VRAM available for AI model inference. This determines which models and quantization levels you can run locally.
Yes, AMD Instinct MI210 64GB is excellent for running LLMs locally with top compatibility scores above 80/100.
For coding on AMD Instinct MI210 64GB, we recommend Qwen3-Coder-Next. It achieves 75.2 tokens per second with 86K context window. Qwen3-Coder-Next is a specialized fit for Coding. It is a recent-generation family, which helps on current local SOTA workloads. It should run, but memory headroom will be limited. Context coverage stays within the requested workload envelope. Known distribution channels: huggingface, ollama, lm-studio.
There are 4 upgrade path(s) from AMD Instinct MI210 64GB: Mac Studio M3 Ultra 96GB, MacBook Pro M3 Max 128GB. Upgrading would unlock larger models and faster inference speeds.
Yes, AMD Instinct MI210 64GB with 64 GB of usable memory can run Flux.1 Dev at FP16 natively. Flux is a 12B parameter diffusion transformer that produces high-quality images. You can also run the Schnell variant for faster generation.
AMD Instinct MI210 64GB (64 GB VRAM) can handle various AI generation tasks beyond LLMs. For image generation, SDXL and Stable Diffusion 3.5 run well. Flux.1 Dev also runs natively for state-of-the-art image quality. For video, LTX Video 2.3 can generate short clips. Check the AI Capability Matrix above for detailed compatibility.
AMD Instinct MI210 64GB is excellent for AI image generation. With 64 GB of usable memory, it runs all major diffusion models including Flux.1, SDXL, and Stable Diffusion 3.5 at full precision. You can generate high-resolution images quickly and even handle video generation models.
Yes, AMD Instinct MI210 64GB with 64 GB of usable memory can run Qwen 3.5 27B at Q8 (near-lossless, ~28.9 GB) or even FP16 (~55.4 GB) depending on your context needs. This setup provides an excellent experience with this model. Use Ollama or vLLM for best results.
With 64 GB VRAM on AMD Instinct MI210 64GB, use Q8_0 for most models — it is near-lossless and you have the memory for it. For 70B+ models, Q6_K offers excellent quality. Reserve Q4_K_M for 100B+ models or when you need maximum context length.
AMD Instinct MI210 64GB already has strong memory bandwidth, so the next limit is often memory capacity and context headroom rather than raw decode speed. For local LLMs, fit first and bandwidth second is the right mental model.
Compare with similar
