Lucie 7B — Hardware Requirements & GPU Compatibility
Chat
Lucie 7B is a 6.7B-parameter open language model from OpenLLM-France. It supports a context window of up to 32,000 tokens. At Q4_K_M it needs about 4.59 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 16K)Best on 24 GB (Q4_K_M · ~143 tok/s · 31K)Macs from 16 GB (Q4_K_M · ~31 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Lucie 7B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve OpenLLM-France/Lucie-7B --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (5 GB headroom) · Q4_K_M
- Generation speed
- ~51 tok/s
- generation speed
- Cost per 1M output tokens
- $0.45
- per 1M output tokens
How Much VRAM Does Lucie 7B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.4 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 31K context · ~192 tok/s | |
| 3.8 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 31K context · ~171 tok/s | |
| 4.6 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 31K context · ~143 tok/s | |
| 5.3 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 31K context · ~123 tok/s | |
| 6.1 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 31K context · ~107 tok/s | |
| 7.3 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 31K context · ~90 tok/s | |
| 14.0 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 31K context · ~47 tok/s |
Selected Q4_K_M
4-bit medium quantization6.5GBat 16K context
- Weights
- 4.0 GB
- KV cache
- 2.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 17.5 GB free · ~143 tok/s
≥50 tok/s needs ≥353 GB/s · RTX 5090 ~254, RTX 3090 Ti ~143
Which Hardware Can Run Lucie 7B?
Q4_K_M · 4.6 GBLucie 7B (Q4_K_M) requires 4.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 6+ GB is recommended. Using the full 32K context window can add up to 3.9 GB, bringing total usage to 8.5 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 151 devices with unified memory can run Lucie 7B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 1.5 GB free · up to 16K ctx
16 GPUs · 2 device families
RTX 3080~108Simulate output on RTX 3080RTX 2080 Ti~87Simulate output on RTX 2080 TiRTX 3070 Ti~86Simulate output on RTX 3070 TiOrin Nano~14Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~10Simulate output on iPhone 1720 GB
fits · 13.5 GB free · up to 31K ctx
1 GPU
RX 7900 XT~105Simulate output on RX 7900 XT32–40 GB
fits · 25.5 GB free · up to 31K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~254Simulate output on RTX 5090M5 Max36 GB~70Simulate output on Mac Studio M5 Max (36 GB)M532 GB~23Simulate output on MacBook Air 13" M5 (32 GB)Orin~29Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~19Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Llava 1.5 7B HFllava-hf | — | 5 GB | ~141 | same size |
| Chatglm3 6BZ.ai | — | 5.2 GB | ~159 | same size |
| Baichuan2 7B Basebaichuan-inc | — | 5 GB | ~142 | same size |
| Internlm 7BInternLM | — | 15.4 GB | ~43 | same size |
| Olmo Hybrid 7BAllen AI | — | 22.4 GB | ~43 | same size |
| Granite 4.0 H TinyIBM | — | 5.8 GB | ~271 | same size |
Specifications
- Publisher
- OpenLLM-France
- Parameters
- 6.7B
- Architecture
- LlamaForCausalLM
- Context Length
- 32,000 tokens
- Vocabulary Size
- 65,024
- Release Date
- 2024-10-10
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Lucie 7B need?
Lucie 7B requires 4.6 GB of VRAM at Q4_K_M, or 14.0 GB at BF16. Full 32K context adds up to 3.9 GB (8.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 6.7B × 4.8 bits ÷ 8 = 4 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 4.5 GB (at full 32K context)
VRAM usage by quantization
What's the best quantization for Lucie 7B?
For Lucie 7B, Q4_K_M (4.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (5.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 3.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Lucie 7B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Lucie 7B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 4.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Lucie 7B locally?
Yes — Lucie 7B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Lucie 7B?
At Q4_K_M, Lucie 7B can reach ~1046 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~143 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 4.59 × 0.65 = ~1133 tok/s
Estimated speed at Q4_K_M (4.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Lucie 7B?
At Q4_K_M, the download is about 4.02 GB. The full-precision BF16 version is 13.41 GB. The smallest option (Q2_K) is 2.85 GB.
Which GPUs can run Lucie 7B?
52 consumer GPUs can run Lucie 7B at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Lucie 7B?
151 devices with unified memory can run Lucie 7B at Q4_K_M (4.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.