GPT NeoX 20B Erebus Q8 0 GGUF — Hardware Requirements & GPU Compatibility
Chat
GPT NeoX 20B Erebus Q8 0 GGUF is a 20B-parameter open language model from YorkieOH10. At Q8_0 it needs about 22.00 GB of VRAM — see which GPUs and Macs can run it below.
83 downloads
4 likesSpecifications
- Publisher
- YorkieOH10
- Parameters
- 20B
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does GPT NeoX 20B Erebus Q8 0 GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q8_0 | 8.00 | 22 GB | — | 20.00 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run GPT NeoX 20B Erebus Q8 0 GGUF?
Q8_0 · 22 GBGPT NeoX 20B Erebus Q8 0 GGUF (Q8_0) requires 22 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 29+ GB is recommended. 5 GPUs can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Which Devices Can Run GPT NeoX 20B Erebus Q8 0 GGUF?
Q8_0 · 22 GB21 devices with unified memory can run GPT NeoX 20B Erebus Q8 0 GGUF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does GPT NeoX 20B Erebus Q8 0 GGUF need?
GPT NeoX 20B Erebus Q8 0 GGUF requires 22 GB of VRAM at Q8_0.
VRAM = Weights + KV Cache + Overhead
Weights = 20B × 8 bits ÷ 8 = 20 GB
KV Cache + Overhead ≈ 2 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q8_022.0 GB- Can I run GPT NeoX 20B Erebus Q8 0 GGUF on a Mac?
GPT NeoX 20B Erebus Q8 0 GGUF requires at least 22 GB at Q8_0, 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 GPT NeoX 20B Erebus Q8 0 GGUF locally?
Yes — GPT NeoX 20B Erebus Q8 0 GGUF can run locally on consumer hardware. At Q8_0 quantization it needs 22 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GPT NeoX 20B Erebus Q8 0 GGUF?
At Q8_0, GPT NeoX 20B Erebus Q8 0 GGUF can reach ~133 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~30 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 ÷ 22.0 × 0.55 = ~133 tok/s
Estimated speed at Q8_0 (22 GB)
~133 tok/s~30 tok/s~99 tok/s~82 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of GPT NeoX 20B Erebus Q8 0 GGUF?
At Q8_0, the download is about 20.00 GB.
- Which GPUs can run GPT NeoX 20B Erebus Q8 0 GGUF?
5 consumer GPUs can run GPT NeoX 20B Erebus Q8 0 GGUF at Q8_0 (22 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
- Which devices can run GPT NeoX 20B Erebus Q8 0 GGUF?
21 devices with unified memory can run GPT NeoX 20B Erebus Q8 0 GGUF at Q8_0 (22 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.