EuroLLM 1.7B Instruct — Hardware Requirements & GPU Compatibility
Chat
7.8K downloads
97 likesSpecifications
- Publisher
- utter-project
- Parameters
- 1.7B
- Architecture
- LlamaForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 128,000
- Release Date
- 2024-12-16
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does EuroLLM 1.7B Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 3.8 GB | 4.0 GB | 3.31 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run EuroLLM 1.7B Instruct?
BF16 · 3.8 GBEuroLLM 1.7B Instruct (BF16) requires 3.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 5+ GB is recommended. Using the full 4K context window can add up to 0.2 GB, bringing total usage to 4.0 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run EuroLLM 1.7B Instruct?
BF16 · 3.8 GB33 devices with unified memory can run EuroLLM 1.7B Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does EuroLLM 1.7B Instruct need?
EuroLLM 1.7B Instruct requires 3.8 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.7B × 16 bits ÷ 8 = 3.3 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 0.7 GB (at full 4K context)
VRAM usage by quantization
BF163.8 GBBF16 + full context4.0 GB- Can I run EuroLLM 1.7B Instruct on a Mac?
EuroLLM 1.7B Instruct requires at least 3.8 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run EuroLLM 1.7B Instruct locally?
Yes — EuroLLM 1.7B Instruct can run locally on consumer hardware. At BF16 quantization it needs 3.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is EuroLLM 1.7B Instruct?
At BF16, EuroLLM 1.7B Instruct can reach ~763 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~172 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 3.8 × 0.55 = ~763 tok/s
Estimated speed at BF16 (3.8 GB)
AMD Instinct MI300X~763 tok/sNVIDIA GeForce RTX 4090~172 tok/sNVIDIA H100 SXM~570 tok/sAMD Instinct MI250X~472 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of EuroLLM 1.7B Instruct?
At BF16, the download is about 3.31 GB.
- Which GPUs can run EuroLLM 1.7B Instruct?
35 consumer GPUs can run EuroLLM 1.7B Instruct at BF16 (3.8 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run EuroLLM 1.7B Instruct?
33 devices with unified memory can run EuroLLM 1.7B Instruct at BF16 (3.8 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.