← All GPUs
AMD · Datacenter (used) · CDNA (gfx908)
AMD Instinct MI100
Still on the ROCm 7.x support list (gfx908), unlike the MI50; passive, needs forced airflow.
VRAM
32 GB
HBM2 ECC
Memory bandwidth
1,200 GB/s
FP16 compute
184.6 TFLOPS
dense tensor
Price
Used only
used price not tracked yet
What fits at 4-bit
The 4-bit file plus 8,192 tokens of context and 1.5 GB of overhead, against the VRAM of 1 and 2 cards. Speeds are measured medians where someone has published a run at that card count; a blank speed means no run, not a slow one. Machine pages carry estimates for the gaps.
| Model | Needs | 1 card (32 GB) | 2 cards (64 GB) |
|---|---|---|---|
| Qwen3.5 4B4B · Q4_K_M | 4.3 GB | fits | fits |
| Llama 3.1 8B Instruct8B · Q4_K_M | 7.1 GB | fits | fits |
| Qwen3 8B8.2B · Q4_K_M | 7.3 GB | fits | fits |
| Gemma 4 E4B IT8B · Q4_K_M | 6.5 GB | fits | fits |
| Granite 4.2 8B8.8B · Q4_K_M | 7.9 GB | fits | fits |
| Qwen3.5 9B9B · Q4_K_M | 7.0 GB | fits | fits |
| Gemma 4 12B IT11.95B · Q4_K_M | 8.2 GB | fits | fits |
| Ministral 3 14B Reasoning (2512)13.9B · Q4_K_M | 10.4 GB | fits | fits |
| Phi-414.7B · Q4_K_M | 11.3 GB | fits | fits |
| gpt-oss-20b21B, 3.6B active · MXFP4 (native) | 12.5 GB | fits | fits |
| Devstral Small 2 24B (2512)24B · Q4_K_M | 16.1 GB | fits | fits |
| Qwen3.6 27B27B · Q4_K_M | 17.7 GB | fits | fits |
| Gemma 4 26B-A4B IT25.2B, 3.8B active · Q4_K_M | 17.4 GB | fits | fits |
| Qwen3.8 27B27B · Q4_K_M | 18.2 GB | fits | fits |
| Granite 4.2 30B29.3B · Q4_K_M | 20.3 GB | fits | fits |
| Gemma 4 31B IT30.7B · Q4_K_M | 18.9 GB | fits | fits |
| Qwen3 Coder 30B-A3B Instruct30.5B, 3.3B active · Q4_K_M | 19.5 GB | fits | fits |
| Ornith 1.5 35B-A3B35B, 3B active · Q4_K_M | 21.9 GB | fits | fits |
| Qwen3.6 35B-A3B35B, 3B active · Q4_K_M | 22.4 GB | fits | fits |
| Nemotron 3.5 Lightning 30B-A3B30B, 3B active · Q4_K_M | 25.3 GB | fits | fits |
| Llama 3.3 70B Instruct70B · Q4_K_M | 43.6 GB | too large | fits |
| Qwen3 Coder Next80B, 3B active · Q4_K_M | 46.9 GB | too large | fits |
| gpt-oss-120b117B, 5.1B active · MXFP4 (native) | 60.2 GB | too large | 84 tok/smedian of 4 runs |
| Llama 4 Scout 17B-16E Instruct109B, 17B active · Q4_K_M | 62.4 GB | too large | fits |
Measured speeds
2 cards
| Model | Quant | Backend | Generation | Prompt | Context | Source |
|---|---|---|---|---|---|---|
| gpt-oss-120b | MXFP4 MoE | llama.cpp (build not stated) ROCm | 97 tok/s | 1,180 tok/s512-token prompt | 0 | llama.cpp benchmark discussion2025-10 |
| gpt-oss-120b | MXFP4 MoE | llama.cpp (build not stated) ROCm | 86 tok/s | 1,030 tok/s512-token prompt | 0 | llama.cpp benchmark discussion2025-11 |
| gpt-oss-120b | MXFP4 MoE | llama.cpp (build not stated) ROCm | 83 tok/s | 1,029 tok/s512-token prompt | 0 | llama.cpp benchmark discussion2025-11 |
| gpt-oss-120b | MXFP4 MoE | llama.cpp (build not stated) ROCm | 83 tok/s | 1,055 tok/s512-token prompt | 0 | llama.cpp benchmark discussion2025-10 |
Specifications
- Memory
- 32 GB HBM2 ECC
- FP16 basis
- AMD 'Peak Half Precision (FP16)' matrix figure; bfloat16 is 92.3 TFLOPS.
- Board power
- 300 W
- Slots
- 2
- Length
- 267 mm
- PCIe
- Gen 4 x16
- NVLink
- No
- Cooling
- Passive (needs server airflow)
- Software
- ROCm, Vulkan
- Released
- 2020
- Availability
- used only
- Price basis
- Not sold new.
- Maker page
- amd.com
Sources
- amd.com: 32 GB HBM2, 1.2 TB/s, 300 W, PCIe 4.0 x16, passive, 267 mm double slot, 184.6 TFLOPS FP16, 92.3 bf16
- rocm.docs.amd.com: ROCm 7.14 supported-GPU list: 7900 XTX/W7900 (gfx1100), 9070 XT/R9700 (gfx1201), MI100 (gfx908) supported; MI50 (gfx906) not supported; Radeon RX cards Ubuntu-only