AMD Instinct MI325X

Hardware · AMD

What AI models can the AMD Instinct MI325X run?

VRAM
256 GB
Usable for models
256 GB
Memory bandwidth
6,000 GB/s
FP16 compute
163.4 TFLOPS
Released
2024
587 / 622 LLMs run Best: Qwen3.8 Flash Next (125B-A6B) 61 / 61 Image models run Best: MiniMax H3 Image 43 / 43 Video models run Best: LTX-2.5 (22B, video + audio) 70 / 70 Decision models run Best: Qwen3 Reranker 4B

More about this hardware

MakerAMD
TypeDatacenter GPU module
InterfacePCIe 5.0

Apps that run models well on the AMD Instinct MI325X

Linux

  1. vLLMThe full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
  2. LemonadeAMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.
  3. LM StudioPoint-and-click: search, download and chat in one window.
  4. OllamaOne command with Ollama’s own build of this model.

Windows

  1. LemonadeAMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.
  2. LM StudioPoint-and-click: search, download and chat in one window.
  3. OllamaOne command with Ollama’s own build of this model.
  4. llama.cppUsually the first to support new model architectures.

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

Best LLMs for the AMD Instinct MI325X

Quality Model Quant Memory Speed Runs
96Excellent quality (A+) · 96 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 Flash Next (125B-A6B)Alibaba Q8_0 204 GB 177 tok/s Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.7 (230B-A10B)MiniMax Q6_K 203 GB 170 tok/s Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Step 3.7 Flash (198B-A11B)StepFun Q6_K 179 GB 164 tok/s Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Nex N2.6 (321B-A18B)Nex-AGI Q4_K_M 209 GB 161 tok/s Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. GLM-5.3 Flash (320B-A18B)Zhipu AI Q4_K_M 209 GB 161 tok/s Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at F16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9BNVIDIA F16 163 GB 95.9 tok/s Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Flash (310B-A15B)Xiaomi Q4_K_M 203 GB 175 tok/s Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. MiniMax M2.5 (230B-A10B)MiniMax Q6_K 203 GB 170 tok/s Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Step 3.5 Flash (196B-A11B)StepFun Q6_K 177 GB 164 tok/s Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Kolibri 1 (78B-A3.5B)Aleph Alpha F16 170 GB 149 tok/s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Inkling Small (276B-A12B)Thinking Machines Lab Q5_K_M 203 GB 173 tok/s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Naive N0.5 Flash (309B-A15.5B)Naive AI Q4_K_M 202 GB 172 tok/s Runs great

Best Image models for the AMD Instinct MI325X

Quality Model Quant Memory Speed Runs
93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiniMax H3 ImageMiniMax FP16 138 GB 9.0 s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. HunyuanImage 3.0 (80B-A13B)Tencent FP16 170 GB 54 s Slow
92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Cosmos3-Super Text2Image (64B)NVIDIA FP16 133 GB 36 s Runs well
92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [dev]Black Forest Labs FP16 116 GB 32 s Runs well
92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Krea 2 TurboKrea FP16 37.4 GB 3.9 s Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Qwen-Image 2.1 TurboAlibaba FP16 46.7 GB 10 s Runs great

Best Video models for the AMD Instinct MI325X

Quality Model Quant Memory Speed Runs
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. LTX-2.5 (22B, video + audio)Lightricks FP16 82.5 GB 82 s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. MiniMax H3 (33B, video + audio)MiniMax FP16 113 GB 15.6 min Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Cosmos3-Super Image2Video (64B)NVIDIA FP16 139 GB 33.7 min Slow
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. LTX-2.3Lightricks FP16 75.4 GB 6.0 min Runs well
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. LTX-2 (19B, video + audio)Lightricks FP16 75.4 GB 6.0 min Runs well

Best Decision models for the AMD Instinct MI325X

Quality Model Quant Memory Speed Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Reranker 4BAlibaba F16 21.7 GB 27 ms Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Reranker 8BAlibaba F16 30.1 GB 51 ms Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Skywork Reward V2 Llama 3.1 8BSkywork F16 17.5 GB 99 ms Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at F16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. zerank-2ZeroEntropy F16 21.7 GB 27 ms Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. GLiDE 27BFastino F16 59.3 GB 86 ms Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3.5Jina AI F16 14.8 GB 7.4 ms Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Shieldstral 1.0 3BMistral AI F16 21.3 GB 26 ms Runs great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Intern-Decision 4BShanghai AI Lab F16 22.5 GB 19 ms Runs great

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?