AMD - data center GPU - verified
Local LLMs that run on AMD Instinct MI355X (288 GB)
By this directory's rule of thumb, 49 of 63 open-weight models fit in the 288 GB of GPU memory on the Instinct MI355X. The largest by total parameters is Llama 4 Maverick 17B-128E Instruct (401.6B), whose smallest non-MLX download is 242.8 GB, the Q4_K_M GGUF build from unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF.
- Models that fit
- 49 of 63
- Memory
- 288 GB
- Memory type
- HBM3E
- Bandwidth
- 8,000 GB/s
Spec sheet
- Memory
- 288 GB
- Memory type
- HBM3E
- Unified memory
- No
- Bandwidth
- 8,000 GB/s
- Released
- 2025
AMD states peak memory bandwidth as 8 TB/s (converted to GB/s by x1000) and launch date 6/12/2025.
Source: AMD spec page (amd.com)
49 models that fit in 288 GB
Total params, largest first| Model | Total params | Smallest download | Quant | Commercial |
|---|---|---|---|---|
| Llama 4 Maverick 17B-128E InstructMeta | 401.6B17B active | 242.8 GB | Q4_K_MGGUF | Commercial use: Conditions |
| GLM-4.7Z.ai | 358.3B | 216.5 GB | Q4_K_MGGUF | Commercial use: Yes |
| GLM-4.6Z.ai | 356.8B | 215.6 GB | Q4_K_MGGUF | Commercial use: Yes |
| GLM-5.3-FlashZ.ai | 321.3B18B active | 199.7 GB | UD-Q4_K_XLGGUF | Commercial use: Yes |
| MiMo-V2.6-Flash-RLXiaomi MiMo | 310.8B15B active | 167.4 GB | MXFP4GGUF | Commercial use: Yes |
| Hy3Tencent | 298.8B21B active | 182.3 GB | Q4_K_MGGUF | Commercial use: Yes |
| Step 3.7 FlashStepFun | 201.4B11B active | 111.5 GB | Q4_K_SGGUF | Commercial use: Yes |
| Mistral Medium 3.5 128BMistral AI | 127.7B | 74.9 GB | Q4_K_MGGUF | Commercial use: Conditions |
| Devstral 2 123B Instruct 2512Mistral AI | 125B | 74.9 GB | Q4_K_MGGUF | Commercial use: Conditions |
| NVIDIA Nemotron 3.5 Super VL 120B-A12BNVIDIA | 124.5B12B active | 71.8 GB | Q4_0GGUF | Commercial use: Yes |
| Mistral Small 4 119B (2603)Mistral AI | 119.4B6.5B active | 73.8 GB | UD-Q4_K_MGGUF | Commercial use: Yes |
| gpt-oss-120bOpenAI | 116.8B5.1B active | 62.8 GB | Q4_K_MGGUF | Commercial use: Yes |
| Cohere Command A (03-2025)Cohere | 111.1B | 67.1 GB | Q4_K_MGGUF | Commercial use: No |
| GLM-4.5-AirZ.ai | 110.5B12B active | 73.0 GB | Q4_K_MGGUF | Commercial use: Yes |
| Llama 4 Scout 17B-16E InstructMeta | 108.6B17B active | 65.4 GB | Q4_K_MGGUF | Commercial use: Conditions |
| GLM-4.6VZ.ai | 107.7B | 70.6 GB | Q4_K_MGGUF | Commercial use: Yes |
| Qwen3-Coder-NextAlibaba Cloud (Qwen) | 79.7B3B active | 48.4 GB | Q4_K_MGGUF | Commercial use: Yes |
| NVIDIA Nemotron 3.5 Bolt 74B-A9BNVIDIA | 74.9B9B active | 22.0 GB | 24GB (native 2-bit)GGUF | Commercial use: Yes |
| AI21 Jamba2 MiniAI21 Labs | 51.6B12B active | 31.2 GB | Q4_K_MGGUF | Commercial use: Yes |
| Qwen3.6-35B-A3BAlibaba Cloud (Qwen) | 36B3B active | 22.1 GB | UD-Q4_K_MGGUF | Commercial use: Yes |
| Cohere Aya Expanse 32BCohere | 32.3B | 19.8 GB | Q4_K_MGGUF | Commercial use: No |
| Ai2 Olmo 3.1 32B ThinkAi2 | 32.2B | 19.5 GB | Q4_K_MGGUF | Commercial use: Yes |
| NVIDIA Nemotron 3.5 Lightning 30B-A3BNVIDIA | 31.6B3B active | 18.9 GB | Q4_0GGUF | Commercial use: Yes |
| Gemma 4 31BGoogle | 31.3B | 17.7 GB | Q4_0 (QAT)GGUF | Commercial use: Yes |
| IBM Granite 4.2 30BIBM | 29.3B | 17.7 GB | Q4_K_MGGUF | Commercial use: Yes |
| Qwen3.8-27BAlibaba Cloud (Qwen) | 27.8B | 16.5 GB | UD-Q4_K_MGGUF | Commercial use: Yes |
| Gemma 4 26B A4BGoogle | 25.8B3.8B active | 14.4 GB | Q4_0 (QAT)GGUF | Commercial use: Yes |
| Devstral Small 2 24B Instruct 2512Mistral AI | 24B | 14.3 GB | Q4_K_MGGUF | Commercial use: Yes |
| Liquid AI LFM2.5-24B-A2BLiquid AI | 24B2.5B active | 14.5 GB | Q4_K_MGGUF | Commercial use: Conditions |
| gpt-oss-20bOpenAI | 20.9B3.6B active | 11.6 GB | Q4_K_MGGUF | Commercial use: Yes |
| Phi-4-reasoning-vision-15BMicrosoft | 15.1B | 30.2 GB | BF16Official weights | Commercial use: Yes |
| Phi-4Microsoft | 14.7B | 9.1 GB | Q4_KGGUF | Commercial use: Yes |
| Phi-4-reasoning-plusMicrosoft | 14.7B | 9.1 GB | Q4_K_MGGUF | Commercial use: Yes |
| Ministral 3 14B Instruct 2512Mistral AI | 13.9B | 8.2 GB | Q4_K_MGGUF | Commercial use: Yes |
| Gemma 4 12BGoogle | 12B | 7.0 GB | Q4_0 (QAT)GGUF | Commercial use: Yes |
| Qwen3.5-9BAlibaba Cloud (Qwen) | 9.7B | 5.7 GB | Q4_K_MGGUF | Commercial use: Yes |
| Ministral 3 8B Instruct 2512Mistral AI | 8.9B | 5.2 GB | Q4_K_MGGUF | Commercial use: Yes |
| IBM Granite 4.2 8BIBM | 8.8B | 5.3 GB | Q4_K_MGGUF | Commercial use: Yes |
| Cohere Command R7B (12-2024)Cohere | 8B | 5.1 GB | Q4_K_MGGUF | Commercial use: No |
| Gemma 4 E4BGoogle | 8B | 5.0 GB | Q4_K_MGGUF | Commercial use: Yes |
| Ai2 Olmo Hybrid Instruct DPO 7BAi2 | 7.4B | 14.9 GB | BF16Official weights | Commercial use: Yes |
| Gemma 4 E2BGoogle | 5.1B | 3.1 GB | Q4_K_MGGUF | Commercial use: Yes |
| Qwen3.5-4BAlibaba Cloud (Qwen) | 4.7B | 2.7 GB | Q4_K_MGGUF | Commercial use: Yes |
| Ministral 3 3B Instruct 2512Mistral AI | 3.8B | 2.1 GB | Q4_K_MGGUF | Commercial use: Yes |
| Phi-4-mini-instructMicrosoft | 3.8B | 2.5 GB | Q4_K_MGGUF | Commercial use: Yes |
| Phi-4-mini-reasoningMicrosoft | 3.8B | 2.5 GB | Q4_K_MGGUF | Commercial use: Yes |
| Liquid AI LFM2.5-2.6BLiquid AI | 2.7B | 1.7 GB | Q4_K_MGGUF | Commercial use: Conditions |
| Qwen3.5-2BAlibaba Cloud (Qwen) | 2.3B | 1.3 GB | Q4_K_MGGUF | Commercial use: Yes |
| Qwen3.5-0.8BAlibaba Cloud (Qwen) | 0.9B | 0.5 GB | Q4_K_MGGUF | Commercial use: Yes |
1 more model fits in 288 GB only as an MLX build, which runs on Apple silicon only: MiniMax-M3.
The rest of the 63 need more than 288 GB. Browse every local model.
Compare all 33 GPUs and Macs by memory, bandwidth and how many models fit.
FAQ
How many local LLMs can the Instinct MI355X run?
49 of the 63 open-weight models in this directory fit, with 288 GB of GPU memory, by this site's rule of thumb that the smallest non-MLX download is at most 85% of the memory. MLX builds do not count here: they run on Apple silicon only.
Can the Instinct MI355X run Llama 4 Maverick 17B-128E Instruct?
Yes, by this directory's rule of thumb: its smallest non-MLX download, 242.8 GB, is at most 85% of 288 GB (244.8 GB), the Q4_K_M GGUF build from unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF. That leaves room for the context. It is a memory check, not a speed estimate.
Can the Instinct MI355X run NVIDIA Nemotron 3.5 Super VL 120B-A12B?
Yes, by this directory's rule of thumb: its smallest non-MLX download, 71.8 GB, is at most 85% of 288 GB (244.8 GB), the Q4_0 GGUF build from ggml-org/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF. That leaves room for the context. It is a memory check, not a speed estimate.
Can the Instinct MI355X run MiniMax-M3?
Not by this directory's rule of thumb: its smallest non-MLX download, 264.9 GB, is more than 85% of 288 GB (244.8 GB). It needs more memory than any single device in this list.
Can the Instinct MI355X use system RAM for bigger models?
This page only counts models that fit entirely in the 288 GB of GPU memory. Runtimes can offload layers to system RAM, but this directory does not list or measure that.
What memory bandwidth does the Instinct MI355X have?
AMD states 8,000 GB/s of memory bandwidth (HBM3E). From the spec notes: AMD states peak memory bandwidth as 8 TB/s (converted to GB/s by x1000) and launch date 6/12/2025. This page does not turn bandwidth into a speed estimate.
Newsletter
New open weights, every week
One email per week. New model releases, open-weight drops and what they mean for what you build.
Keep exploring
Best local AI models
Our curated picks by hardware tier, with benchmarks and the reasoning.
Model API pricing and specs
First-party prices per 1M tokens when you would rather call an API.
AI benchmark leaderboards
Sourced scores, for when you need to compare quality.
Setup guides
Point your coding tools at the model you picked.