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 MI300X 192GB is AMD's flagship CDNA 3 discrete GPU accelerator, targeting LLM inference and training at scale. With 192 GB of HBM3 memory and 5.3 TB/s of bandwidth, it outspecifies the NVIDIA H100 80GB in raw memory capacity and bandwidth. The 1307 TFLOPS FP16 compute, FP8 support, and full ROCm maturity make it AMD's primary datacenter AI product and the main alternative to NVIDIA in large-scale inference deployments.
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) | Runs natively | Wan Video 14B |
Architecture
CDNA 3 powers the Instinct MI300X (GPU-only, 192 GB HBM3) and MI300A (APU with integrated CPU). It features advanced packaging with up to 12 chiplets and native FP8 support for AI inference.
AI Relevance
The MI300X with 192 GB HBM3 can hold even the largest open-weight models (70B+ at full precision) entirely in GPU memory. FP8 support and mature ROCm stack make it a serious competitor to NVIDIA H100 for AI inference.
購入アドバイス
ローカルAIに最適な選択
上位50モデル中39モデルを快適に実行 — ローカル推論の万能選手です。
192.0 GB
VRAM
$15,000
希望小売価格
$78/GB
GBあたりのコスト
このGPUに最適なモデル
What will limit you first
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Best upgrade itinerary
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Unlocks 4 additional models that do not fit on the current setup.
もっと余裕が欲しいですか？ AMD Instinct MI325X 256GB (256.0 GB VRAM) が次のステップアップです。
Chat
SQwen 3.5 122B A10B 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, lm-studio.
Coding
SDevstral 2 123B Instruct is a specialized fit for Coding. 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, lm-studio.
Agentic Coding
SDevstral 2 123B Instruct is a specialized fit for Agentic Coding. 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, lm-studio.
Reasoning
SDevstral 2 123B Instruct 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, lm-studio.
RAG
SQwen 3.5 122B A10B 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, lm-studio.
DeepSeek V4 Flash
Qwen 3.5 122B A10B
Devstral 2 123B InstructMistral Small 4 119BQwen 3 235B A22B
GPT-OSS 120B
Command A 111BPixtral Large 124BQwen 2.5 VL 72BQwen3-Coder-NextQwen3-Coder 30B A3B InstructQwen 3.6 35B A3BLeanstral 119B A6BQwen 3.5 27BQwen3-VL 30B A3B InstructQwen 3.6 27BQwen 3.5 35B A3BQwen 3 32BMagistral Small 2507Devstral Small 2 24B InstructQwen 3 30B A3BQwen 3.5 9B
Nemotron 3 Nano 30BQwen 3 14BDevstral Small 1.1
Phi-4-reasoning-plus 14BQwen 3 8B
Gemma 4 31BGPT-OSS 20BNemotron Cascade 2 30B A3BQwen 3.5 4B
EXAONE 4.0 32BMinistral 3 14BNemotron Nano 8BPhi-4 Mini Reasoning 4BDeepSeek Coder V2 236B
Jina Embeddings v3
BGE M3Qwen 3.5 397B A17B
Kimi K2.5Kimi K2.6DeepSeek V4 Pro
GLM-5.2GLM-5.1GLM-5DeepSeek V3.2Qwen3-Coder 480B A35B InstructDeepSeek R1 671BDeepSeek V3.1 671Bもう少しで届く
もう少しメモリがあれば動く高品質モデル
Image & Video Generation
56 of 56 models can generate images or video on your AMD Instinct MI300X 192GB
| Model | Max Resolution | Gen Time | Grade |
|---|---|---|---|
| SD TurboImage | 512×512 | 0ms | S |
| Stable Diffusion 1.5Image | 512×768 | 100ms | S |
| Realistic Vision v5.1Image | 512×768 | 100ms | S |
| DreamShaper 8Image | 512×768 | 100ms | S |
| LCM DreamShaper v7Image | 512×768 | 0ms | S |
| PixArt-SigmaImage | 1024×1024 | 200ms | S |
| FramePack I2VVideo | 1280×720 | 400ms/frame | S |
| SDXL TurboImage | 512×512 | 0ms | S |
| SDXL LightningImage | 1024×1024 | 100ms | S |
| Stable Diffusion XL 1.0Image | 1024×1024 | 200ms | S |
| Playground v2.5Image | 1024×1024 | 400ms | S |
| RealVisXL v5.0Image | 1024×1024 | 300ms | S |
| DreamShaper XLImage | 1024×1024 | 300ms | S |
| Juggernaut XL v9Image | 1024×1024 | 300ms | S |
| Animagine XL 3.1Image | 1024×1024 | 300ms | S |
| Pony Diffusion V6 XLImage | 1024×1024 | 300ms | S |
| Animagine XL 4.0Image | 1024×1024 | 300ms | S |
| Illustrious XLImage | 1024×1024 | 300ms | S |
| Wan Video 2.1 1.3BVideo | 480×832 | 200ms/frame | S |
| Stable Diffusion 3.5 MediumImage | 1024×1024 | 400ms | S |
| Flux.2 Klein 4BImage | 1024×1024 | 100ms | S |
| LTX Video 2BVideo | 1280×720 | 200ms/frame | S |
| KolorsImage | 1024×1024 | 500ms | S |
| Stable CascadeImage | 1024×1024 | 600ms | S |
| AuraFlow v0.3Image | 1536×1536 | ~1.1s | S |
| Stable Diffusion 3.5 LargeImage | 1024×1024 | ~1.3s | S |
| Stable Diffusion 3.5 Large TurboImage | 1024×1024 | 200ms | S |
| CogVideoX 2BVideo | 720×480 | 200ms/frame | S |
| HunyuanVideoVideo | 720×1280 | 400ms/frame | S |
| ChromaImage | 1024×1024 | 200ms | S |
| Z-Image TurboImage | 1536×1536 | 300ms | S |
| Flux.1 DevImage | 1024×1024 | ~1.1s | S |
| Flux.1 SchnellImage | 1024×1024 | 200ms | S |
| LTX Video 13BVideo | 1280×720 | 400ms/frame | S |
| Flux.1 Kontext DevImage | 1024×1024 | ~1.2s | S |
| AnimateDiff v1.5.3Video | 512×768 | 100ms/frame | S |
| Cosmos Diffusion 7BVideo | 1024×576 | 400ms/frame | S |
| CogVideoX 5BVideo | 720×480 | 300ms/frame | S |
| Wan2.2 TI2V 5BVideo | 832×480 | 300ms/frame | S |
| Flux.2 Klein 9BImage | 1024×1024 | 100ms | S |
| Flux.1 Fill DevImage | 1024×1024 | ~1s | S |
| Krea 2Image | 1024×1024 | 300ms | S |
| Sulphur 2Video | 1280×720 | 400ms/frame | S |
| Ideogram 4Image | 2048×2048 | 300ms | S |
| Mochi 1 PreviewVideo | 848×480 | 400ms/frame | S |
| HunyuanVideo 1.5Video | 720×1280 | 400ms/frame | S |
| Helios 14BVideo | 1280×720 | 500ms/frame | S |
| SkyReels V2 14BVideo | 1280×720 | 500ms/frame | S |
| Wan Video 2.1 14BVideo | 720×1280 | 500ms/frame | S |
| Wan Video 2.2 14BVideo | 720×1280 | 500ms/frame | S |
| Qwen ImageImage | 1024×1024 | 400ms | S |
| Qwen Image EditImage | 1024×1024 | 400ms | S |
| LTX-2 22BVideo | 1920×1088 | 600ms/frame | S |
| Flux.2 DevImage | 1024×1024 | ~11.6s | S |
| MAGI-1Video | 1280×720 | 600ms/frame | S |
| HunyuanImage 3.0Image | 1024×1024 | 700ms | B |
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.
Multi-GPU scaling
Scale out with multiple GPUs for larger models. Infinity Fabric provides 896 GB/s inter-GPU bandwidth with 12% overhead.
| Config | Effective memory | Models that fit | Est. bandwidth |
|---|---|---|---|
| 1× AMD | 192 GB | 364/380 | 5,300 GB/s |
| 2× AMD | 384 GB | 371/380 | 9,328 GB/s |
| 4× AMD | 768 GB | 379/380 | 18,656 GB/s |
| 8× AMD | 1536 GB | 380/380 | 37,312 GB/s |
Model counts use default quantization at coding workload settings. Multi-GPU scaling factor: 0.88× per additional GPU.
Upgrade paths
See what you unlock with more powerful hardware
アップグレードオプション
Unlocks 16 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 161%.
Infinity Fabric gives this scale-out path a cleaner inter-GPU story than PCIe-only builds.
〜$15,000 MSRP
Unlocks 4 additional models that do not fit on the current setup.
〜$20,000 MSRP
Unlocks 5 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 16%.
〜$8,000 MSRP
AMD Instinct MI300X 192GB (192 GB VRAM) can run these top models: DeepSeek V4 Flash (score: 96/100), Qwen 3.5 122B A10B (score: 95/100), Devstral 2 123B Instruct (score: 95/100). See the full compatibility list above.
AMD Instinct MI300X 192GB has 192 GB of VRAM available for AI model inference. This determines which models and quantization levels you can run locally.
Yes, AMD Instinct MI300X 192GB is excellent for running LLMs locally with top compatibility scores above 80/100.
For coding on AMD Instinct MI300X 192GB, we recommend Devstral 2 123B Instruct. It achieves 46.8 tokens per second with 212K context window. Devstral 2 123B Instruct is a specialized fit for Coding. 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, lm-studio.
There are 3 upgrade path(s) from AMD Instinct MI300X 192GB: AMD Instinct MI300X 192GB, AMD Instinct MI325X 256GB. Upgrading would unlock larger models and faster inference speeds.
Yes, AMD Instinct MI300X 192GB with 192 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 MI300X 192GB (192 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 MI300X 192GB is excellent for AI image generation. With 192 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 MI300X 192GB with 192 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 192 GB VRAM on AMD Instinct MI300X 192GB, 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 MI300X 192GB 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.
AMD Instinct MI300X 192GB supports up to 8× GPU scaling via Infinity Fabric at 896 GB/s. With 8× GPUs, you get 1536 GB effective memory with a 0.88× scaling factor per GPU. This enables running models like Qwen 3.5 397B A17B and Kimi K2.5 that don't fit on a single card.
Infinity Fabric is recommended for AMD Instinct MI300X 192GB multi-GPU inference, providing 896 GB/s interconnect bandwidth with only 12% scaling overhead. PCIe-only setups work but have higher overhead (~25%) due to limited inter-GPU bandwidth.
Compare with similar
