GhostFace 24B V1 — Hardware Requirements & GPU Compatibility
Chat
260 downloads
10 likesSpecifications
- Publisher
- Naphula
- Parameters
- 23.6B
- Architecture
- MistralForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 131,078
- Release Date
- 2026-03-04
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does GhostFace 24B V1 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 47.9 GB | 74.3 GB | 47.14 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run GhostFace 24B V1?
BF16 · 47.9 GBGhostFace 24B V1 (BF16) requires 47.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 63+ GB is recommended. Using the full 131K context window can add up to 26.4 GB, bringing total usage to 74.3 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run GhostFace 24B V1?
BF16 · 47.9 GB11 devices with unified memory can run GhostFace 24B V1, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).
Runs great
— Plenty of headroom
Related Models
Frequently Asked Questions
- How much VRAM does GhostFace 24B V1 need?
GhostFace 24B V1 requires 47.9 GB of VRAM at BF16. Full 131K context adds up to 26.4 GB (74.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 23.6B × 16 bits ÷ 8 = 47.1 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 27.2 GB (at full 131K context)
VRAM usage by quantization
BF1647.9 GBBF16 + full context74.3 GB- Can NVIDIA GeForce RTX 5090 run GhostFace 24B V1?
No — GhostFace 24B V1 requires at least 47.9 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run GhostFace 24B V1 on a Mac?
GhostFace 24B V1 requires at least 47.9 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 GhostFace 24B V1 locally?
Yes — GhostFace 24B V1 can run locally on consumer hardware. At BF16 quantization it needs 47.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GhostFace 24B V1?
At BF16, GhostFace 24B V1 can reach ~61 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 ÷ 47.9 × 0.55 = ~61 tok/s
Estimated speed at BF16 (47.9 GB)
AMD Instinct MI300X~61 tok/sNVIDIA H100 SXM~46 tok/sAMD Instinct MI250X~38 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of GhostFace 24B V1?
At BF16, the download is about 47.14 GB.
- Which GPUs can run GhostFace 24B V1?
No single consumer GPU has enough VRAM to run GhostFace 24B V1 at BF16 (47.9 GB). Multi-GPU or professional hardware is required.
- Which devices can run GhostFace 24B V1?
11 devices with unified memory can run GhostFace 24B V1 at BF16 (47.9 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.