AMD Instinct MI100

Hardware · AMD

What AI models can the AMD Instinct MI100 run?

VRAM
32.0 GB
Usable for models
32.0 GB
Memory bandwidth
1,229 GB/s
FP16 compute
46.1 TFLOPS
Released
2020
513 / 621 LLMs run Best: Qwen3.8 27B 60 / 61 Image models run Best: Krea 2 Turbo 40 / 43 Video models run Best: LTX-2.5 (22B, video + audio) 68 / 70 Decision models run Best: Qwen3 Reranker 4B

More about this hardware

MakerAMD
TypeWorkstation / datacenter graphics card
InterfacePCIe 4.0

Apps that run models well on the AMD Instinct MI100

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 MI100

Quality Model Quant Memory Speed Runs
92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 27BAlibaba Q5_K_M 22.5 GB 38.6 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. Gemma 4 26B-A4BGoogle Q6_K 23.8 GB 128 tok/s Runs great
91Excellent quality (A+) · 91 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. Qwen3.6 27BAlibaba Q5_K_M 22.5 GB 38.6 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. Nanbeige4.3 33BBOSS Zhipin (Nanbeige) Q4_K_M 24.1 GB 39.2 tok/s Runs great
92Excellent quality (A+) · 92 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. Qwen3.6 35B-A3BAlibaba Q6_K 31.8 GB 144 tok/s Runs welltight fit
92Excellent quality (A+) · 92 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. MiniCPM-V 4.7 35B-A3BOpenBMB Q6_K 31.2 GB 144 tok/s Runs welltight fit
92Excellent quality (A+) · 92 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. Qwen3.5 35B-A3BAlibaba Q6_K 31.8 GB 144 tok/s Runs welltight fit
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. Qwen3.5 27BAlibaba Q5_K_M 22.5 GB 38.6 tok/s Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B)Nex-AGI Q6_K 31.2 GB 144 tok/s Runs welltight fit
88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B)Kuaishou Q5_K_M 27.0 GB 159 tok/s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Sage-A1.5 35B-A3BInternScience Q6_K 31.8 GB 144 tok/s Runs welltight fit
89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Muse Glimmer 30BMeta Q5_K_M 23.5 GB 36.0 tok/s Runs great

Best Image models for the AMD Instinct MI100

Quality Model Quant Memory Speed Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Krea 2 TurboKrea FP8 20.2 GB 9.0 s Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. FLUX 3 Image KleinBlack Forest Labs FP16 22.4 GB 13 s Runs great
85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. ERNIE-Image TurboBaidu FP16 26.4 GB 7.4 s Runs great
84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Z-Image TurboAlibaba (Tongyi) FP16 22.7 GB 5.8 s Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 9BBlack Forest Labs Q8 GGUF 20.5 GB 4.8 s Runs great
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 4BBlack Forest Labs FP16 18.1 GB 2.3 s Runs great

Best Video models for the AMD Instinct MI100

Quality Model Quant Memory Speed Runs
81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. LTX-2.5 (22B, video + audio)Lightricks Q4 GGUF 26.8 GB 4.4 min Runs wellencoder in RAM
66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. LTX-Video 13B 0.9.8 (distilled)Lightricks FP8 30.1 GB 2.1 min Runs welltight fit
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Bernini-R A14B (video generation + editing)ByteDance FP8 26.0 GB 25.1 min Slow
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. HY-OmniWeaving (8.3B, unified video)Tencent FP8 24.6 GB 18.5 min Slow
72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. FramePack I2V (HunyuanVideo 13B)lllyasviel FP8 28.2 GB 13.9 min Slowtight fit

Best Decision models for the AMD Instinct MI100

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 10.5 GB 89 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 10.5 GB 89 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 3.6 GB 17 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 10.1 GB 86 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 11.3 GB 60 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. Jina Reranker v3Jina AI F16 3.6 GB 17 ms Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Reranker 8BAlibaba Q8_0 11.2 GB 163 ms Runs well
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. d1 3BLiquid AI F16 8.5 GB 42 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?