Intel Data Center GPU Max 1100
The Intel Data Center GPU Max 1100 has 48 GB VRAM and 1229 GB/s memory bandwidth. It can run 52 of our 71 tracked models natively in VRAM at 8k context.
With 48 GB HBM2e, the Intel Data Center GPU Max 1100 is a datacenter-tier GPU that can run 52 models natively. It handles 70B-class models at Q4 quantization.
The Intel Data Center GPU Max 1100 offers 48GB of HBM2e at 1,229 GB/s in a lower-power (300W) package compared to the 1550. It fits 30B–34B models at Q8 or 70B models at Q4 in memory, and is used in supercomputing installations alongside CPU tiles in the Aurora system at Argonne National Laboratory.
Intel Data Center GPU Max 1100: 2022 Xe-HPC Ponte Vecchio with 48GB HBM2e at 1,229 GB/s — mid-tier Intel HPC GPU.
30B-34B at Q8 or 70B at Q4 fit in 48GB. Strong bandwidth for datacenter inference.
SYCL/oneAPI gives best performance; llama.cpp SYCL backend supported. Typically cloud/HPC-accessed.
| Vendor | Intel |
| Architecture | Xe-HPC (Ponte Vecchio) |
| VRAM | 48 GB |
| Memory type | HBM2e |
| Memory bandwidth | 1229 GB/s |
| Compute backend | VULKAN |
| Tier | Datacenter |
| Released | 2022 |
| Models (native) | 52 / 71 |
| Models (offload) | 2 / 71 |
Software: Typically accessed via cloud. Uses SYCL/oneAPI for best performance; llama.cpp SYCL backend supported.
Popular models for this GPU
Models this GPU runs natively in VRAM (52)
- Nemotron 3 Super 120B120B · MMLU-Pro 83.7Q2_K · ~342.4 t/s
- GPT-OSS 120B117B · MMLU-Pro 80.7Q2_K · ~821.8 t/s
- Llama 4 Scout 109B109B · MMLU-Pro 74.3Q2_K · ~241.7 t/s
- GLM-4.5 Air 106B106B · MMLU-Pro 81.4Q2_K · ~342.4 t/s
- GLM-4.6V 106B106B · MMLU-Pro 79.9Q2_K · ~342.4 t/s
- Qwen 2.5 72B Instruct72B · MMLU-Pro 71.1Q3_K_M · ~39.7 t/s
- Llama 3.3 70B Instruct70B · MMLU-Pro 68.9Q3_K_M · ~40.8 t/s
- DeepSeek R1 Distill Llama 70B70B · MMLU-Pro 70.0Q3_K_M · ~40.8 t/s
- Llama 3.1 70B Instruct70B · MMLU-Pro 66.4Q3_K_M · ~40.8 t/s
- Mixtral 8x7B Instruct v0.146.7B · MMLU-Pro 29.7Q6_K · ~127.8 t/s
- Command-R 35B35B · MMLU-Pro 33.0Q6_K · ~42.8 t/s
- Qwen 3.5 35B-A3B (MoE)35B · MMLU-Pro 84.2Q8_0 · ~450.6 t/s
- Qwen 3.6 35B35B · MMLU-Pro 85.2Q8_0 · ~35.1 t/s
- Yi 1.5 34B Chat34.4B · MMLU-Pro 37.0Q8_0 · ~35.7 t/s
- Qwen3 32B32.8B · MMLU-Pro 65.5Q8_0 · ~37.5 t/s
- Qwen 2.5 32B Instruct32.5B · MMLU-Pro 69.0Q8_0 · ~37.8 t/s
- Qwen 2.5 Coder 32B Instruct32.5B · MMLU-Pro 50.4Q8_0 · ~37.8 t/s
- DeepSeek R1 Distill Qwen 32B32.5B · MMLU-Pro 65.0Q8_0 · ~37.8 t/s
- Nemotron 3 Nano 30B32B · MMLU-Pro 78.3Q8_0 · ~450.6 t/s
- Gemma 4 31B31B · MMLU-Pro 85.2Q8_0 · ~39.6 t/s
- Qwen3 30B-A3B (MoE)30B · MMLU-Pro 61.5Q8_0 · ~450.6 t/s
- Gemma 2 27B Instruct27.2B · MMLU-Pro 38.0Q8_0 · ~45.2 t/s
- Gemma 3 27B Instruct27B · MMLU-Pro 67.5Q8_0 · ~45.5 t/s
- Qwen 3.6 27B27B · MMLU-Pro 86.2Q8_0 · ~45.5 t/s
- Gemma 4 26B (MoE)26B · MMLU-Pro 82.6Q8_0 · ~355.8 t/s
- Mistral Small 3.1 24B Instruct24B · MMLU-Pro 66.8Q8_0 · ~51.2 t/s
- Mistral Small 22B22.2B · MMLU-Pro 49.2Q8_0 · ~55.4 t/s
- GPT-OSS 20B21B · MMLU-Pro 67.9Q8_0 · ~338 t/s
- Qwen3 14B14.8B · MMLU-Pro 61.0BF16 · ~41.5 t/s
- Qwen 2.5 14B Instruct14.7B · MMLU-Pro 63.7BF16 · ~41.8 t/s
- Phi-4 14B Instruct14B · MMLU-Pro 70.4BF16 · ~43.9 t/s
- Mistral Nemo 12B Instruct12.2B · MMLU-Pro 35.6BF16 · ~50.4 t/s
- Gemma 3 12B Instruct12.2B · MMLU-Pro 60.6BF16 · ~50.4 t/s
- Gemma 2 9B Instruct9.2B · MMLU-Pro 32.0FP32 · ~33.4 t/s
- Llama 3.1 8B Instruct8B · MMLU-Pro 48.3FP32 · ~38.4 t/s
- DeepSeek R1 Distill Llama 8B8B · MMLU-Pro 41.0FP32 · ~38.4 t/s
- Qwen3 8B8B · MMLU-Pro 56.7FP32 · ~38.4 t/s
- Qwen 2.5 7B Instruct7.6B · MMLU-Pro 56.3FP32 · ~40.4 t/s
- Mistral 7B Instruct v0.37.25B · MMLU-Pro 30.0FP32 · ~42.4 t/s
- Gemma 3 4B Instruct4B · MMLU-Pro 43.6FP32 · ~76.8 t/s
- Gemma 4 E4B4B · MMLU-Pro 69.4FP32 · ~76.8 t/s
- Phi-3.5 Mini Instruct3.8B · MMLU-Pro 47.4FP32 · ~80.9 t/s
- Llama 3.2 3B Instruct3.2B · MMLU-Pro 24.0FP32 · ~96 t/s
- Qwen 2.5 3B Instruct3.1B · MMLU-Pro 32.4FP32 · ~99.1 t/s
- Gemma 2 2B Instruct2.6B · MMLU-Pro 17.8FP32 · ~118.2 t/s
- Gemma 4 E2B2B · MMLU-Pro 60.0FP32 · ~153.6 t/s
- SmolLM2 1.7B Instruct1.7B · MMLU-Pro 19.0FP32 · ~180.7 t/s
- Qwen 2.5 1.5B Instruct1.5B · MMLU-Pro 16.8FP32 · ~204.8 t/s
- Llama 3.2 1B Instruct1.24B · MMLU-Pro 12.5FP32 · ~247.8 t/s
- Gemma 3 1B Instruct1B · MMLU-Pro 14.7FP32 · ~307.3 t/s
- Qwen 2.5 0.5B Instruct0.5B · MMLU-Pro 10.0FP32 · ~614.5 t/s
- SmolLM2 360M Instruct0.36B · MMLU-Pro 8.0FP32 · ~853.5 t/s
Models that fit with CPU offload (2)
These use system RAM for layers that don't fit in VRAM — expect much slower inference.
Too large for this GPU (17)
Models mentioned
Nemotron 3 Super 120B120B (12B active)
NVIDIAQ3_K_M rec.
GPT-OSS 120B117B (5B active)
OpenAIQ4_K_M rec.
Llama 4 Scout 109B109B (17B active)
MetaQ4_K_M rec.
GLM-4.5 Air 106B106B (12B active)
Z.aiQ3_K_M rec.
GLM-4.6V 106B106B (12B active)
Z.aiQ3_K_M rec.
Qwen 2.5 72B Instruct72B
AlibabaQ4_K_M rec.
Llama 3.3 70B Instruct70B
MetaQ4_K_M rec.
DeepSeek R1 Distill Llama 70B70B
DeepSeekQ4_K_M rec.
Llama 3.1 70B Instruct70B
MetaQ4_K_M rec.
Mixtral 8x7B Instruct v0.146.7B (12.9B active)
Mistral AIQ4_K_M rec.
Command-R 35B35B
CohereQ4_K_M rec.
Qwen 3.5 35B-A3B (MoE)35B (3B active)
AlibabaQ4_K_M rec.
Qwen 3.6 35B35B
AlibabaQ4_K_M rec.
Yi 1.5 34B Chat34.4B
01.AIQ4_K_M rec.
Qwen3 32B32.8B
AlibabaQ4_K_M rec.
Qwen 2.5 32B Instruct32.5B
AlibabaQ4_K_M rec.
Qwen 2.5 Coder 32B Instruct32.5B
AlibabaQ4_K_M rec.
DeepSeek R1 Distill Qwen 32B32.5B
DeepSeekQ4_K_M rec.
Nemotron 3 Nano 30B32B (3B active)
NVIDIAQ5_K_M rec.
Gemma 4 31B31B
GoogleQ4_K_M rec.
Qwen3 30B-A3B (MoE)30B (3B active)
AlibabaQ4_K_M rec.
Gemma 2 27B Instruct27.2B
GoogleQ4_K_M rec.
Gemma 3 27B Instruct27B
GoogleQ4_K_M rec.
Qwen 3.6 27B27B
AlibabaQ4_K_M rec.
Gemma 4 26B (MoE)26B (3.8B active)
GoogleQ4_K_M rec.
Mistral Small 3.1 24B Instruct24B
Mistral AIQ4_K_M rec.
Mistral Small 22B22.2B
Mistral AIQ4_K_M rec.
GPT-OSS 20B21B (4B active)
OpenAIQ5_K_M rec.
Qwen3 14B14.8B
AlibabaQ5_K_M rec.
Qwen 2.5 14B Instruct14.7B
AlibabaQ5_K_M rec.
Phi-4 14B Instruct14B
MicrosoftQ5_K_M rec.
Mistral Nemo 12B Instruct12.2B
Mistral AIQ5_K_M rec.
Gemma 3 12B Instruct12.2B
GoogleQ5_K_M rec.
Gemma 2 9B Instruct9.2B
GoogleQ5_K_M rec.
Llama 3.1 8B Instruct8B
MetaQ5_K_M rec.
DeepSeek R1 Distill Llama 8B8B
DeepSeekQ5_K_M rec.
Qwen3 8B8B
AlibabaQ5_K_M rec.
Qwen 2.5 7B Instruct7.6B
AlibabaQ6_K rec.
Mistral 7B Instruct v0.37.25B
Mistral AIQ6_K rec.
Gemma 3 4B Instruct4B
GoogleQ6_K rec.
Gemma 4 E4B4B
GoogleQ5_K_M rec.
Phi-3.5 Mini Instruct3.8B
MicrosoftQ6_K rec.
Llama 3.2 3B Instruct3.2B
MetaQ6_K rec.
Qwen 2.5 3B Instruct3.1B
AlibabaQ6_K rec.
Gemma 2 2B Instruct2.6B
GoogleQ8_0 rec.
Gemma 4 E2B2B
GoogleQ8_0 rec.
SmolLM2 1.7B Instruct1.7B
Hugging FaceQ8_0 rec.
Qwen 2.5 1.5B Instruct1.5B
AlibabaQ8_0 rec.
Llama 3.2 1B Instruct1.24B
MetaQ8_0 rec.
Gemma 3 1B Instruct1B
GoogleQ8_0 rec.
Qwen 2.5 0.5B Instruct0.5B
AlibabaQ8_0 rec.
SmolLM2 360M Instruct0.36B
Hugging FaceQ8_0 rec.
Frequently asked questions
- How much VRAM does the Intel Data Center GPU Max 1100 have?
- The Intel Data Center GPU Max 1100 has 48 GB of HBM2e with 1229 GB/s memory bandwidth.
- What is the Intel Data Center GPU Max 1100 best for?
- With 48 GB of VRAM, the Intel Data Center GPU Max 1100 is ideal for running 70B-class models at Q4 quantization and large MoE models — a workstation sweet spot for local inference.
- What LLMs can the Intel Data Center GPU Max 1100 run locally?
- The Intel Data Center GPU Max 1100 can run 52 of the 71 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.3 70B Instruct at Q3_K_M, Llama 3.1 8B Instruct at FP32, Llama 3.2 3B Instruct at FP32.
- Can the Intel Data Center GPU Max 1100 run Llama 3.3 70B Instruct?
- Yes. The Intel Data Center GPU Max 1100 runs Llama 3.3 70B Instruct natively in VRAM at Q3_K_M quantization, achieving approximately 40.8 tokens per second.
- Can the Intel Data Center GPU Max 1100 run Qwen 3.6 27B?
- Yes. The Intel Data Center GPU Max 1100 runs Qwen 3.6 27B natively in VRAM at Q8_0 quantization, achieving approximately 45.5 tokens per second.
- Can the Intel Data Center GPU Max 1100 run Llama 3.1 8B Instruct?
- Yes. The Intel Data Center GPU Max 1100 runs Llama 3.1 8B Instruct natively in VRAM at FP32 quantization, achieving approximately 38.4 tokens per second.