BBrainOutput

Compatible models for Supermicro SuperServer (H200)

Open models graded for the Supermicro SuperServer (H200) (top config: 1024GB, ~1128GB AI memory), best fit first. Lower configurations run fewer of these.

  • DeepSeek-R1 671B (MoE)
    DeepSeek · ~671B · 128K ctx · MIT

    Fits at Q8_0 (~700GB) with ~292.6GB headroom — about 1 concurrent instance.

    Q8_0 · ~700GBRuns well
  • Llama 3.1 405B
    Llama · ~405B · 128K ctx · Llama Community License

    Fits at FP16 (~810GB) with ~182.6GB headroom — about 1 concurrent instance.

    FP16 · ~810GBRuns well
  • Qwen3 235B-A22B (MoE)
    Qwen · ~235B · 128K ctx · Apache-2.0

    Fits at FP16 (~470GB) with ~522.6GB headroom — about 2 concurrent instances.

    FP16 · ~470GBRuns well
  • Qwen2.5 72B
    Qwen · ~72B · 128K ctx · Qwen License

    Fits at FP16 (~145GB) with ~847.6GB headroom — about 6 concurrent instances.

    FP16 · ~145GBRuns well
  • Llama 3.1 70B
    Llama · ~70B · 128K ctx · Llama Community License

    Fits at FP16 (~140GB) with ~852.6GB headroom — about 7 concurrent instances.

    FP16 · ~140GBRuns well
  • Llama 3.3 70B
    Llama · ~70B · 128K ctx · Llama Community License

    Fits at FP16 (~140GB) with ~852.6GB headroom — about 7 concurrent instances.

    FP16 · ~140GBRuns well
  • DeepSeek-R1 Distill Llama 70B
    DeepSeek · ~70B · 128K ctx · MIT

    Fits at FP16 (~140GB) with ~852.6GB headroom — about 7 concurrent instances.

    FP16 · ~140GBRuns well
  • Mixtral 8x7B (MoE)
    Mistral · ~47B · 32K ctx · Apache-2.0

    Fits at FP16 (~90GB) with ~902.6GB headroom — about 11 concurrent instances.

    FP16 · ~90GBRuns well
  • CodeLlama 34B
    CodeLlama · ~34B · 16K ctx · Llama Community License

    Fits at FP16 (~68GB) with ~924.6GB headroom — about 14 concurrent instances.

    FP16 · ~68GBRuns well
  • Qwen2.5 32B
    Qwen · ~32B · 128K ctx · Apache-2.0

    Fits at FP16 (~64GB) with ~928.6GB headroom — about 15 concurrent instances.

    FP16 · ~64GBRuns well
  • Qwen3 32B
    Qwen · ~32B · 128K ctx · Apache-2.0

    Fits at FP16 (~64GB) with ~928.6GB headroom — about 15 concurrent instances.

    FP16 · ~64GBRuns well
  • DeepSeek-R1 Distill 32B
    DeepSeek · ~32B · 128K ctx · MIT

    Fits at FP16 (~64GB) with ~928.6GB headroom — about 15 concurrent instances.

    FP16 · ~64GBRuns well
  • Qwen2.5-Coder 32B
    Qwen · ~32B · 128K ctx · Apache-2.0

    Fits at FP16 (~64GB) with ~928.6GB headroom — about 15 concurrent instances.

    FP16 · ~64GBRuns well
  • Gemma 2 27B
    Gemma · ~27B · 8K ctx · Gemma Terms of Use

    Fits at FP16 (~54GB) with ~938.6GB headroom — about 18 concurrent instances.

    FP16 · ~54GBRuns well
  • Gemma 3 27B
    Gemma 3 · ~27B · 128K ctx · Gemma Terms of Use

    Fits at FP16 (~54GB) with ~938.6GB headroom — about 18 concurrent instances.

    FP16 · ~54GBRuns well
  • Mistral Small 24B
    Mistral · ~24B · 32K ctx · Apache-2.0

    Fits at FP16 (~48GB) with ~944.6GB headroom — about 20 concurrent instances.

    FP16 · ~48GBRuns well
  • DeepSeek-Coder V2 (class)
    DeepSeek · ~16B · 128K ctx · DeepSeek License

    Fits at FP16 (~33GB) with ~959.6GB headroom — about 30 concurrent instances.

    FP16 · ~33GBRuns well
  • StarCoder2 15B
    StarCoder · ~15B · 16K ctx · BigCode OpenRAIL-M

    Fits at FP16 (~30GB) with ~962.6GB headroom — about 33 concurrent instances.

    FP16 · ~30GBRuns well
  • Qwen2.5 14B
    Qwen · ~14B · 128K ctx · Apache-2.0

    Fits at FP16 (~30GB) with ~962.6GB headroom — about 33 concurrent instances.

    FP16 · ~30GBRuns well
  • Qwen3 14B
    Qwen · ~14B · 128K ctx · Apache-2.0

    Fits at FP16 (~30GB) with ~962.6GB headroom — about 33 concurrent instances.

    FP16 · ~30GBRuns well
  • Phi-3 Medium (14B)
    Phi · ~14B · 128K ctx · MIT

    Fits at FP16 (~28GB) with ~964.6GB headroom — about 35 concurrent instances.

    FP16 · ~28GBRuns well
  • Phi-4 (14B)
    Phi · ~14B · 16K ctx · MIT

    Fits at FP16 (~28GB) with ~964.6GB headroom — about 35 concurrent instances.

    FP16 · ~28GBRuns well
  • DeepSeek-R1 Distill 14B
    DeepSeek · ~14B · 128K ctx · MIT

    Fits at FP16 (~30GB) with ~962.6GB headroom — about 33 concurrent instances.

    FP16 · ~30GBRuns well
  • Qwen2.5-Coder 14B
    Qwen · ~14B · 128K ctx · Apache-2.0

    Fits at FP16 (~30GB) with ~962.6GB headroom — about 33 concurrent instances.

    FP16 · ~30GBRuns well
  • CodeLlama 13B
    CodeLlama · ~13B · 16K ctx · Llama Community License

    Fits at FP16 (~26GB) with ~966.6GB headroom — about 38 concurrent instances.

    FP16 · ~26GBRuns well
  • Gemma 3 12B
    Gemma 3 · ~12B · 128K ctx · Gemma Terms of Use

    Fits at FP16 (~24GB) with ~968.6GB headroom — about 41 concurrent instances.

    FP16 · ~24GBRuns well
  • Mistral Nemo 12B
    Mistral · ~12B · 128K ctx · Apache-2.0

    Fits at FP16 (~24GB) with ~968.6GB headroom — about 41 concurrent instances.

    FP16 · ~24GBRuns well
  • Gemma 2 9B
    Gemma · ~9B · 8K ctx · Gemma Terms of Use

    Fits at FP16 (~19GB) with ~973.6GB headroom — about 52 concurrent instances.

    FP16 · ~19GBRuns well
  • Llama 3.1 8B
    Llama · ~8B · 128K ctx · Llama Community License

    Fits at FP16 (~17GB) with ~975.6GB headroom — about 58 concurrent instances.

    FP16 · ~17GBRuns well
  • Qwen3 8B
    Qwen · ~8B · 128K ctx · Apache-2.0

    Fits at FP16 (~17GB) with ~975.6GB headroom — about 58 concurrent instances.

    FP16 · ~17GBRuns well
  • Granite 3 8B
    Granite · ~8B · 128K ctx · Apache-2.0

    Fits at FP16 (~17GB) with ~975.6GB headroom — about 58 concurrent instances.

    FP16 · ~17GBRuns well
  • DeepSeek-R1 Distill 8B
    DeepSeek · ~8B · 128K ctx · MIT

    Fits at FP16 (~17GB) with ~975.6GB headroom — about 58 concurrent instances.

    FP16 · ~17GBRuns well
  • Qwen2.5 7B Instruct
    Qwen2.5 · ~7.6B · 33K ctx · apache-2.0

    Fits at FP16 (~15.2GB) with ~977.4GB headroom — about 65 concurrent instances.

    FP16 · ~15.2GBRuns well
  • Qwen2.5 Coder 7B Instruct
    Qwen2.5 · ~7.6B · 131K ctx · apache-2.0

    Fits at FP16 (~15.2GB) with ~977.4GB headroom — about 65 concurrent instances.

    FP16 · ~15.2GBRuns well
  • Qwen2.5 7B
    Qwen · ~7B · 128K ctx · Apache-2.0

    Fits at FP16 (~15GB) with ~977.6GB headroom — about 66 concurrent instances.

    FP16 · ~15GBRuns well
  • Mistral 7B
    Mistral · ~7B · 32K ctx · Apache-2.0

    Fits at FP16 (~15GB) with ~977.6GB headroom — about 66 concurrent instances.

    FP16 · ~15GBRuns well
  • Qwen2.5-Coder 7B
    Qwen · ~7B · 128K ctx · Apache-2.0

    Fits at FP16 (~15GB) with ~977.6GB headroom — about 66 concurrent instances.

    FP16 · ~15GBRuns well
  • CodeLlama 7B
    CodeLlama · ~7B · 16K ctx · Llama Community License

    Fits at FP16 (~14GB) with ~978.6GB headroom — about 70 concurrent instances.

    FP16 · ~14GBRuns well
  • StarCoder2 7B
    StarCoder · ~7B · 16K ctx · BigCode OpenRAIL-M

    Fits at FP16 (~14GB) with ~978.6GB headroom — about 70 concurrent instances.

    FP16 · ~14GBRuns well
  • Gemma 3 4B
    Gemma 3 · ~4B · 128K ctx · Gemma Terms of Use

    Fits at FP16 (~8GB) with ~984.6GB headroom — about 124 concurrent instances.

    FP16 · ~8GBRuns well
  • Phi-3.5 Mini (3.8B)
    Phi · ~3.8B · 128K ctx · MIT

    Fits at FP16 (~8GB) with ~984.6GB headroom — about 124 concurrent instances.

    FP16 · ~8GBRuns well
  • Llama 3.2 3B
    Llama · ~3B · 128K ctx · Llama Community License

    Fits at FP16 (~7GB) with ~985.6GB headroom — about 141 concurrent instances.

    FP16 · ~7GBRuns well
  • Qwen2.5 3B
    Qwen · ~3B · 32K ctx · Qwen Research License

    Fits at FP16 (~6GB) with ~986.6GB headroom — about 165 concurrent instances.

    FP16 · ~6GBRuns well
  • StarCoder2 3B
    StarCoder · ~3B · 16K ctx · BigCode OpenRAIL-M

    Fits at FP16 (~6GB) with ~986.6GB headroom — about 165 concurrent instances.

    FP16 · ~6GBRuns well
  • Gemma 2 2B
    Gemma · ~2B · 8K ctx · Gemma Terms of Use

    Fits at FP16 (~4GB) with ~988.6GB headroom — about 248 concurrent instances.

    FP16 · ~4GBRuns well
  • Granite 3 2B
    Granite · ~2B · 128K ctx · Apache-2.0

    Fits at FP16 (~4GB) with ~988.6GB headroom — about 248 concurrent instances.

    FP16 · ~4GBRuns well
  • SmolLM2 1.7B
    SmolLM · ~1.7B · 8K ctx · Apache-2.0

    Fits at FP16 (~3.4GB) with ~989.2GB headroom — about 291 concurrent instances.

    FP16 · ~3.4GBRuns well
  • Qwen2.5 1.5B
    Qwen · ~1.5B · 32K ctx · Apache-2.0

    Fits at FP16 (~3GB) with ~989.6GB headroom — about 330 concurrent instances.

    FP16 · ~3GBRuns well
  • DeepSeek-R1 Distill 1.5B
    DeepSeek · ~1.5B · 128K ctx · MIT

    Fits at FP16 (~4GB) with ~988.6GB headroom — about 248 concurrent instances.

    FP16 · ~4GBRuns well
  • Qwen2.5-Coder 1.5B
    Qwen · ~1.5B · 32K ctx · Apache-2.0

    Fits at FP16 (~3GB) with ~989.6GB headroom — about 330 concurrent instances.

    FP16 · ~3GBRuns well
  • Llama 3.2 1B
    Llama · ~1B · 128K ctx · Llama Community License

    Fits at FP16 (~3GB) with ~989.6GB headroom — about 330 concurrent instances.

    FP16 · ~3GBRuns well
  • Qwen2.5 0.5B
    Qwen · 32K ctx · Apache-2.0

    Fits at FP16 (~1GB) with ~991.6GB headroom — about 992 concurrent instances.

    FP16 · ~1GBRuns well

All Supermicro SuperServer (H200) configurations →

Run these models on the Supermicro SuperServer (H200)

Run your own AI agents on hardware you control — private by design, no per-seat data leaving your premises. BrainOutput helps you pick the right machine and turn it into a working AI Business OS.