Luciole 8B Base — Hardware Requirements & GPU Compatibility
Chat
Luciole 8B Base is a 8.1B-parameter open language model from OpenLLM-France. It supports a context window of up to 131,072 tokens. At BF16 it needs about 16.89 GB of VRAM — see which GPUs and Macs can run it below.
514 downloads
3 likesSpecifications
- Publisher
- OpenLLM-France
- Parameters
- 8.1B
- Architecture
- NemotronHForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 128,000
- Release Date
- 2026-06-01
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Luciole 8B Base Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 16.9 GB | 44.4 GB | 16.15 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Luciole 8B Base?
BF16 · 16.9 GBLuciole 8B Base (BF16) requires 16.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 22+ GB is recommended. Using the full 131K context window can add up to 27.5 GB, bringing total usage to 44.4 GB. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Luciole 8B Base?
BF16 · 16.9 GB21 devices with unified memory can run Luciole 8B Base, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Luciole 8B Base need?
Luciole 8B Base requires 16.9 GB of VRAM at BF16. Full 131K context adds up to 27.5 GB (44.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.1B × 16 bits ÷ 8 = 16.2 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 28.2 GB (at full 131K context)
VRAM usage by quantization
BF1616.9 GBBF16 + full context44.4 GB- Can I run Luciole 8B Base on a Mac?
Luciole 8B Base requires at least 16.9 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 Luciole 8B Base locally?
Yes — Luciole 8B Base can run locally on consumer hardware. At BF16 quantization it needs 16.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Luciole 8B Base?
At BF16, Luciole 8B Base can reach ~173 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~39 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 ÷ 16.9 × 0.55 = ~173 tok/s
Estimated speed at BF16 (16.9 GB)
~173 tok/s~39 tok/s~129 tok/s~107 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Luciole 8B Base?
At BF16, the download is about 16.15 GB.
- Which GPUs can run Luciole 8B Base?
6 consumer GPUs can run Luciole 8B Base at BF16 (16.9 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Luciole 8B Base?
21 devices with unified memory can run Luciole 8B Base at BF16 (16.9 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.