OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF — Hardware Requirements & GPU Compatibility
ChatCodeReasoning
A GGUF-quantized, abliterated version of OpenAI's GPT-OSS 20B, processed by DavidAU using imatrix quantization for improved quality at lower bit depths. Based on huihui-ai's uncensored abliteration of the original model, this 20-billion-parameter variant removes built-in refusal behaviors while preserving the model's general capabilities. The imatrix quantization technique uses importance-weighted calibration data to minimize quality loss during compression, making this a well-optimized package for local inference. Suitable for users who want an unrestricted general-purpose assistant model at the 20B scale. Runs well on GPUs with 12 to 16 GB of VRAM depending on quantization level.
82.1K downloads
465 likesSpecifications
- Publisher
- DavidAU
- Family
- GPT-OSS
- Parameters
- 20B
- Release Date
- 2025-11-17
- License
- Apache 2.0
Get Started
How Much VRAM Does OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| IQ4_NL | 4.50 | 12.4 GB | — | 11.25 GB | Importance-weighted 4-bit, non-linear |
| Q5_1 | 5.50 | 15.1 GB | — | 13.75 GB | 5-bit legacy quantization with offset |
| Q8_0 | 8.00 | 22 GB | — | 20.00 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF?
Q8_0 · 22 GBOpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix 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 OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF?
Q8_0 · 22 GB21 devices with unified memory can run OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix 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 OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF need?
OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF requires 12.4 GB of VRAM at IQ4_NL, or 22 GB at Q8_0.
VRAM = Weights + KV Cache + Overhead
Weights = 20B × 4.5 bits ÷ 8 = 11.3 GB
KV Cache + Overhead ≈ 1.1 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
IQ4_NL12.4 GB- What's the best quantization for OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF?
For OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF, Q5_1 (15.1 GB) offers the best balance of quality and VRAM usage. Q8_0 (22 GB) provides better quality if you have the VRAM. The smallest option is IQ4_NL at 12.4 GB.
VRAM requirement by quantization
IQ4_NL12.4 GB~88%Q5_1 ★15.1 GB~92%Q8_022.0 GB~99%★ Recommended — best balance of quality and VRAM usage.
- Can I run OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF on a Mac?
OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF requires at least 12.4 GB at IQ4_NL, 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 OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF locally?
Yes — OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF can run locally on consumer hardware. At IQ4_NL quantization it needs 12.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF?
At IQ4_NL, OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF can reach ~236 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~53 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 ÷ 12.4 × 0.55 = ~236 tok/s
Estimated speed at IQ4_NL (12.4 GB)
AMD Instinct MI300X~236 tok/sNVIDIA GeForce RTX 4090~53 tok/sNVIDIA H100 SXM~176 tok/sAMD Instinct MI250X~146 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of OpenAi GPT OSS 20B Abliterated Uncensored NEO Imatrix GGUF?
At IQ4_NL, the download is about 11.25 GB. The full-precision Q8_0 version is 20.00 GB.