AMD Instinct MI210

Hardware · AMD

What AI models can the AMD Instinct MI210 run?

VRAM
64.0 GB
Usable for models
64.0 GB
Memory bandwidth
1,638 GB/s
FP16 compute
45.3 TFLOPS
Released
2022
527 / 621 LLMs run Best: Qwen3.6 35B-A3B 61 / 61 Image models run Best: Krea 2 Turbo 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
TypeWorkstation / datacenter graphics card
InterfacePCIe 4.0

Apps that run models well on the AMD Instinct MI210

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 MI210

Quality Model Quant Memory Speed Runs
93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3BAlibaba Q8_0 42.1 GB 139 tok/s Runs great
93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3BOpenBMB Q8_0 41.3 GB 139 tok/s Runs great
93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3BAlibaba Q8_0 42.1 GB 139 tok/s Runs great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B)Nex-AGI Q8_0 41.2 GB 139 tok/s Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Sage-A1.5 35B-A3BInternScience Q8_0 42.1 GB 139 tok/s Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B)Kuaishou Q8_0 40.7 GB 139 tok/s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Flint (40B-A2.5B)Recursive Q8_0 46.2 GB 151 tok/s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 35B-A3BDeepReinforce Q8_0 42.1 GB 139 tok/s Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Apodex 1.1 Mini (35B-A3B)Apodex Q8_0 42.1 GB 139 tok/s Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.0 35B-A3BDeepReinforce Q8_0 42.1 GB 139 tok/s Runs great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Nemotron 3.5 Bolt 74B-A9BNVIDIA Q4_K_M 49.6 GB 117 tok/s Runs great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Agents-A1 35B-A3BInternScience Q8_0 41.2 GB 139 tok/s Runs great

Best Image models for the AMD Instinct MI210

Quality Model Quant Memory Speed Runs
92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Krea 2 TurboKrea FP16 37.4 GB 10 s Runs great
84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 9BBlack Forest Labs FP16 37.1 GB 4.2 s Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen-Image 2.1 TurboAlibaba FP16 46.7 GB 27 s Runs well
85Excellent quality (A+) · 85 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. ERNIE-Image TurboBaidu FP16 26.4 GB 7.5 s Runs great
91Excellent quality (A+) · 91 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. FLUX 3 Image KleinBlack Forest Labs FP16 22.4 GB 13 s Runs well
84Great quality (A) · 84 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. Z-Image TurboAlibaba (Tongyi) FP16 22.7 GB 5.9 s Runs great

Best Video models for the AMD Instinct MI210

Quality Model Quant Memory Speed Runs
86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. LTX-2.5 (22B, video + audio)Lightricks FP8 48.3 GB 3.2 min Runs great
68Good quality (B) · 68 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. LTX-Video 13B 0.9.8 (distilled)Lightricks FP16 47.9 GB 2.4 min Runs great
84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. LTX-2.3Lightricks FP8 44.3 GB 14.1 min Slow
85Excellent quality (A+) · 85 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. Bernini-R A14B (video generation + editing)ByteDance FP16 46.0 GB 28.2 min Slow
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. LTX-2 (19B, video + audio)Lightricks FP8 44.3 GB 14.1 min Slow

Best Decision models for the AMD Instinct MI210

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 12.1 GB 87 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 12.1 GB 87 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 5.2 GB 16 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 11.7 GB 84 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 12.9 GB 57 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 5.2 GB 16 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 12.8 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 10.1 GB 40 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?