GPT Neox 20B — Hardware Requirements & GPU Compatibility
Chat
GPT Neox 20B is a 20.7B-parameter open language model from EleutherAI. It supports a context window of up to 2,048 tokens. At Q4_K_M it needs about 13.69 GB of VRAM — see which GPUs and Macs can run it below.
649.3K downloads
584 likesSpecifications
- Publisher
- EleutherAI
- Parameters
- 20.7B
- Architecture
- GPTNeoXForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 50,432
- Release Date
- 2024-01-31
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does GPT Neox 20B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 9.7 GB | — | 8.81 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 10.0 GB | — | 9.07 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 11.1 GB | — | 10.11 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 11.4 GB | — | 10.37 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 13.7 GB | — | 12.44 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 16.3 GB | — | 14.78 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 18.8 GB | — | 17.11 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 22.8 GB | — | 20.74 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run GPT Neox 20B?
Q4_K_M · 13.7 GBGPT Neox 20B (Q4_K_M) requires 13.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 18+ GB is recommended. 17 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run GPT Neox 20B?
Q4_K_M · 13.7 GB27 devices with unified memory can run GPT Neox 20B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 (16 GB).
Runs great
— Plenty of headroomBenchmarks
View all 1 →Related Models
Derivatives (3)
Frequently Asked Questions
- How much VRAM does GPT Neox 20B need?
GPT Neox 20B requires 13.7 GB of VRAM at Q4_K_M, or 22.8 GB at Q8_0.
VRAM = Weights + KV Cache + Overhead
Weights = 20.7B × 4.8 bits ÷ 8 = 12.4 GB
KV Cache + Overhead ≈ 1.3 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M13.7 GB- What's the best quantization for GPT Neox 20B?
For GPT Neox 20B, Q4_K_M (13.7 GB) offers the best balance of quality and VRAM usage. Q5_K_S (15.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 6.3 GB.
VRAM requirement by quantization
IQ2_XXS6.3 GBIQ3_XS9.4 GBQ3_K_M11.1 GBQ4_K_S12.8 GBQ4_K_M ★13.7 GBQ8_022.8 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run GPT Neox 20B on a Mac?
GPT Neox 20B requires at least 6.3 GB at IQ2_XXS, 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 locally?
Yes — GPT Neox 20B can run locally on consumer hardware. At Q4_K_M quantization it needs 13.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GPT Neox 20B?
At Q4_K_M, GPT Neox 20B can reach ~213 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~48 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 ÷ 13.7 × 0.55 = ~213 tok/s
Estimated speed at Q4_K_M (13.7 GB)
~213 tok/s~48 tok/s~159 tok/s~132 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?
At Q4_K_M, the download is about 12.44 GB. The full-precision Q8_0 version is 20.74 GB. The smallest option (IQ2_XXS) is 5.70 GB.
- Which GPUs can run GPT Neox 20B?
17 consumer GPUs can run GPT Neox 20B at Q4_K_M (13.7 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3090 Ti, AMD Radeon RX 6800. 5 GPUs have plenty of headroom for comfortable inference.
- Which devices can run GPT Neox 20B?
27 devices with unified memory can run GPT Neox 20B at Q4_K_M (13.7 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.