Luciole 1B Base — Hardware Requirements & GPU Compatibility
Chat
Luciole 1B Base is a 1.3B-parameter open language model from OpenLLM-France. It supports a context window of up to 131,072 tokens. At BF16 it needs about 3.04 GB of VRAM — see which GPUs and Macs can run it below.
360 downloads
3 likesSpecifications
- Publisher
- OpenLLM-France
- Parameters
- 1.3B
- Architecture
- NemotronForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 128,000
- Release Date
- 2026-06-02
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Luciole 1B Base Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 3.0 GB | 9.4 GB | 2.64 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Luciole 1B Base?
BF16 · 3.0 GBLuciole 1B Base (BF16) requires 3.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 131K context window can add up to 6.3 GB, bringing total usage to 9.4 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Luciole 1B Base?
BF16 · 3.0 GB33 devices with unified memory can run Luciole 1B Base, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Luciole 1B Base need?
Luciole 1B Base requires 3.0 GB of VRAM at BF16. Full 131K context adds up to 6.3 GB (9.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.3B × 16 bits ÷ 8 = 2.6 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 6.8 GB (at full 131K context)
VRAM usage by quantization
BF163.0 GBBF16 + full context9.4 GB- Can I run Luciole 1B Base on a Mac?
Luciole 1B Base requires at least 3.0 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 1B Base locally?
Yes — Luciole 1B Base can run locally on consumer hardware. At BF16 quantization it needs 3.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Luciole 1B Base?
At BF16, Luciole 1B Base can reach ~959 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~216 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 ÷ 3.0 × 0.55 = ~959 tok/s
Estimated speed at BF16 (3.0 GB)
~959 tok/s~216 tok/s~717 tok/s~593 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Luciole 1B Base?
At BF16, the download is about 2.64 GB.
- Which GPUs can run Luciole 1B Base?
35 consumer GPUs can run Luciole 1B Base at BF16 (3.0 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 Luciole 1B Base?
33 devices with unified memory can run Luciole 1B Base at BF16 (3.0 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.