ESFT Vanilla Lite — Hardware Requirements & GPU Compatibility
Chat
ESFT Vanilla Lite is a 15.7B-parameter open language model from DeepSeek. It supports a context window of up to 4,096 tokens. At BF16 it needs about 32.17 GB of VRAM — see which GPUs and Macs can run it below.
151 downloads
20 likesSpecifications
- Publisher
- DeepSeek
- Parameters
- 15.7B
- Architecture
- DeepseekV2ForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 102,400
- Release Date
- 2024-07-23
Get Started
HuggingFace
How Much VRAM Does ESFT Vanilla Lite Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 32.2 GB | 32.6 GB | 31.41 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run ESFT Vanilla Lite?
BF16 · 32.2 GBESFT Vanilla Lite (BF16) requires 32.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 42+ GB is recommended. Using the full 4K context window can add up to 0.4 GB, bringing total usage to 32.6 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run ESFT Vanilla Lite?
BF16 · 32.2 GB13 devices with unified memory can run ESFT Vanilla Lite, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (36 GB).
Runs great
— Plenty of headroom
Related Models
Frequently Asked Questions
- How much VRAM does ESFT Vanilla Lite need?
ESFT Vanilla Lite requires 32.2 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 15.7B × 16 bits ÷ 8 = 31.4 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 1.2 GB (at full 4K context)
VRAM usage by quantization
BF1632.2 GBBF16 + full context32.6 GB- Can NVIDIA GeForce RTX 5090 run ESFT Vanilla Lite?
No — ESFT Vanilla Lite requires at least 32.2 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run ESFT Vanilla Lite on a Mac?
ESFT Vanilla Lite requires at least 32.2 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 ESFT Vanilla Lite locally?
Yes — ESFT Vanilla Lite can run locally on consumer hardware. At BF16 quantization it needs 32.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is ESFT Vanilla Lite?
At BF16, ESFT Vanilla Lite can reach ~91 tok/s on AMD Instinct MI300X. 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 ÷ 32.2 × 0.55 = ~91 tok/s
Estimated speed at BF16 (32.2 GB)
~91 tok/s~68 tok/s~56 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of ESFT Vanilla Lite?
At BF16, the download is about 31.41 GB.
- Which GPUs can run ESFT Vanilla Lite?
No single consumer GPU has enough VRAM to run ESFT Vanilla Lite at BF16 (32.2 GB). Multi-GPU or professional hardware is required.
- Which devices can run ESFT Vanilla Lite?
13 devices with unified memory can run ESFT Vanilla Lite at BF16 (32.2 GB), including Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.