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 MI100 32GB was AMD's first CDNA-architecture accelerator, a significant step forward from Vega for HPC and AI workloads. It features 32 GB of HBM2 with 1.2 TB/s of bandwidth and full ROCm support. While superseded by the MI200 and MI300 series, it remains a legitimate ROCm platform for AI inference and is available on the used market at reduced prices. Its Matrix Core units accelerate FP16 and BF16 operations.
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) | Won’t fit | 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) | Won't fit | Wan Video 14B |
Architecture
CDNA is AMD's first compute-focused datacenter GPU architecture, splitting from the gaming-oriented RDNA line. The Instinct MI100 introduced Matrix Cores for accelerated matrix operations.
AI Relevance
Matrix Cores provide hardware-accelerated FP16/BF16 compute for AI training and inference. Full ROCm support makes CDNA GPUs viable for production AI workloads, though the ecosystem lags behind NVIDIA CUDA.
Consejo de compra
Excelente opción para IA local
Ejecuta 26 de 50 modelos principales bien — un todoterreno sólido para inferencia local.
32.0 GB
VRAM
$11,500
PVP
$359/GB
Coste por GB de VRAM
Mejores modelos para esta GPU
What will limit you first
Este setup está bastante equilibrado para este modelo.
No hay grandes señales de alerta
Esta recomendación tiene margen de memoria suficiente y una velocidad estimada razonable para la carga de trabajo seleccionada.
Best upgrade itinerary
Desbloquea 11 modelos adicionales que hoy no caben en tu setup.
¿Quieres más margen? MacBook Pro M1 Max 64GB (64.0 GB unified memory) es el siguiente paso.
Chat
SThis model is a direct match for chat. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
Coding
SThis model is a direct match for coding. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, lm-studio.
Agentic Coding
SThis model is still usable for agentic-coding, but it is not the most specialized pick. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, lm-studio.
Reasoning
SThis model is a direct match for reasoning. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
RAG
SThis model is a direct match for rag. It belongs to a current frontier family for local AI. It should run, but memory headroom will be limited. Known channels: huggingface, ollama, lm-studio.
Qwen3-Coder 30B A3B InstructQwen3-VL 30B A3B InstructQwen 3.5 27BQwen 3 30B A3BQwen 3.6 35B A3B
Magistral Small 2507Devstral Small 2 24B InstructQwen 3.5 35B A3BQwen 3.6 27B
Nemotron 3 Nano 30BNemotron Cascade 2 30B A3BDevstral Small 1.1
GPT-OSS 20BQwen 3 14BQwen 3 32B
Phi-4-reasoning-plus 14BQwen 3.5 9BQwen 3 8BMinistral 3 14B
EXAONE 4.0 32BQwen 3.5 4BNemotron Nano 8BPhi-4 Mini Reasoning 4B
Jina Embeddings v3
Gemma 4 31B
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 111BQwen 2.5 VL 72BGPT-OSS 120B
GLM-5.2Qwen3-Coder-NextGLM-5.1Pixtral Large 124BGLM-5DeepSeek V3.2Qwen 3 235B A22BQwen3-Coder 480B A35B InstructLeanstral 119B A6BDeepSeek Coder V2 236BDeepSeek R1 671BDeepSeek V3.1 671BCasi al alcance
Modelos de alta calidad que necesitan un poco más de memoria
Image & Video Generation
46 of 56 models can generate images or video on your AMD Instinct MI100 32GB
| 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 | ~2.1s | S |
| FramePack I2VVideo | 256×256 | ~3.8s/frame | S |
| SDXL TurboImage | 512×512 | 300ms | S |
| SDXL LightningImage | 1024×1024 | 800ms | S |
| Stable Diffusion XL 1.0Image | 1024×1024 | ~2.1s | S |
| Playground v2.5Image | 1024×1024 | ~3.1s | 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 | ~3.6s | S |
| Flux.2 Klein 4BImage | 1024×1024 | 600ms | S |
| LTX Video 2BVideo | 1280×720 | ~1.8s/frame | S |
| KolorsImage | 1024×1024 | ~4.2s | S |
| Stable CascadeImage | 1024×1024 | ~5.2s | S |
| AuraFlow v0.3Image | 1536×1536 | ~9.4s | S |
| Stable Diffusion 3.5 LargeImage | 1024×1024 | ~11.5s | S |
| Stable Diffusion 3.5 Large TurboImage | 1024×1024 | ~2.1s | S |
| CogVideoX 2BVideo | 720×480 | ~1.8s/frame | S |
| HunyuanVideoVideo | 256×256 | ~3.8s/frame | S |
| ChromaImage | 1024×1024 | ~2.1s | S |
| Z-Image TurboImage | 1536×1536 | ~2.2s | S |
| Flux.1 DevImage | 256×256 | ~16.4s | S |
| Flux.1 SchnellImage | 256×256 | ~3.2s | S |
| LTX Video 13BVideo | 256×256 | ~3.8s/frame | S |
| Flux.1 Kontext DevImage | 256×256 | ~18.2s | S |
| AnimateDiff v1.5.3Video | 512×768 | ~1s/frame | S |
| Cosmos Diffusion 7BVideo | 1024×576 | ~3s/frame | A |
| CogVideoX 5BVideo | 720×480 | ~2.6s/frame | A |
| Wan2.2 TI2V 5BVideo | 832×480 | ~2.6s/frame | A |
| Flux.2 Klein 9BImage | 1024×1024 | ~1s | A |
| Flux.1 Fill DevImage | 256×256 | ~15.5s | B |
| Krea 2Image | 256×256 | ~5s | B |
| Sulphur 2Video | 256×256 | ~6.1s/frame | B |
| Ideogram 4Image | 256×256 | ~4.7s | D |
| Mochi 1 PreviewVideo | 256×256 | ~6.2s/frame | D |
| HunyuanVideo 1.5Video | 256×256 | ~6s/frame | D |
| Helios 14BVideo | 256×256 | ~3.9s/frame | F |
| SkyReels V2 14BVideo | 256×256 | ~3.9s/frame | F |
| Wan Video 2.1 14BVideo | 256×256 | ~3.9s/frame | F |
| Wan Video 2.2 14BVideo | 256×256 | ~3.9s/frame | F |
| Qwen ImageImage | 256×256 | ~3.5s | F |
| Qwen Image EditImage | 256×256 | ~3.5s | F |
| LTX-2 22BVideo | 256×256 | ~4.7s/frame | F |
| Flux.2 DevImage | 256×256 | ~1m 39s | F |
| MAGI-1Video | 256×256 | ~4.9s/frame | F |
| HunyuanImage 3.0Image | 256×256 | ~6.2s | 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
Opciones de mejora
Desbloquea 11 modelos adicionales que hoy no caben en tu setup.
~$2,499 MSRP
Desbloquea 13 modelos adicionales que hoy no caben en tu setup.
~$3,999 MSRP
Desbloquea 26 modelos adicionales que hoy no caben en tu setup.
~$2,499 MSRP
Desbloquea 39 modelos adicionales que hoy no caben en tu setup.
Eleva la velocidad media de decodificación en torno a un 116% en los modelos que sí caben.
~$8,000 MSRP
AMD Instinct MI100 32GB (32 GB VRAM) can run these top models: Qwen3-Coder 30B A3B Instruct (score: 100/100), Qwen3-VL 30B A3B Instruct (score: 99/100), Qwen 3.5 27B (score: 98/100). See the full compatibility list above.
AMD Instinct MI100 32GB has 32 GB of VRAM available for AI model inference. This determines which models and quantization levels you can run locally.
Yes, AMD Instinct MI100 32GB is excellent for running LLMs locally with top compatibility scores above 80/100.
For coding on AMD Instinct MI100 32GB, we recommend Qwen 3.6 27B. It achieves 32.6 tokens per second with 187K context window. This model is a direct match for coding. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, lm-studio.
There are 4 upgrade path(s) from AMD Instinct MI100 32GB: MacBook Pro M1 Max 64GB, Radeon PRO W7900 DS 48GB. Upgrading would unlock larger models and faster inference speeds.
Yes, AMD Instinct MI100 32GB with 32 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 MI100 32GB (32 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 MI100 32GB is excellent for AI image generation. With 32 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 MI100 32GB with 32 GB of usable memory can run Qwen 3.5 27B at Q4_K_M (~16.5 GB) with ~7 GB headroom for context and runtime. Quality at Q4 is very close to full precision for most tasks. Run it with: ollama run qwen3.5:27b
With 32 GB on AMD Instinct MI100 32GB, Q4_K_M is the sweet spot for 27B-35B models, Q6_K for 14B models, and Q8_0 for 8B-9B models. The general rule: use the highest quantization that fits with at least 2-3 GB headroom for KV cache and runtime.
AMD Instinct MI100 32GB 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
