GPT OSS 20B ONNX — Hardware Requirements & GPU Compatibility
Chat
4.8K downloads
10 likesSpecifications
- Publisher
- ONNX Community
- Family
- GPT-OSS
- Parameters
- 20B
- Architecture
- GptOssForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 201,088
- Release Date
- 2026-03-04
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does GPT OSS 20B ONNX Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 8.9 GB | 13.3 GB | 8.50 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 9.1 GB | 13.6 GB | 8.75 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 10.1 GB | 14.6 GB | 9.75 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 10.4 GB | 14.8 GB | 10.00 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 12.4 GB | 16.8 GB | 12.00 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 14.6 GB | 19.1 GB | 14.25 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 16.9 GB | 21.3 GB | 16.50 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 20.4 GB | 24.8 GB | 20.00 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run GPT OSS 20B ONNX?
Q4_K_M · 12.4 GBGPT OSS 20B ONNX (Q4_K_M) requires 12.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 17+ GB is recommended. Using the full 131K context window can add up to 4.5 GB, bringing total usage to 16.8 GB. 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 OSS 20B ONNX?
Q4_K_M · 12.4 GB27 devices with unified memory can run GPT OSS 20B ONNX, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 (16 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does GPT OSS 20B ONNX need?
GPT OSS 20B ONNX requires 12.4 GB of VRAM at Q4_K_M, or 20.4 GB at Q8_0. Full 131K context adds up to 4.5 GB (16.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 20B × 4.8 bits ÷ 8 = 12 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 4.8 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M12.4 GBQ4_K_M + full context16.8 GB- What's the best quantization for GPT OSS 20B ONNX?
For GPT OSS 20B ONNX, Q4_K_M (12.4 GB) offers the best balance of quality and VRAM usage. Q4_K_L (12.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 5.9 GB.
VRAM requirement by quantization
IQ2_XXS5.9 GB~53%Q2_K8.9 GB~75%Q3_K_L10.6 GB~86%Q4_K_M ★12.4 GB~89%Q4_K_L12.6 GB~90%Q8_020.4 GB~99%★ Recommended — best balance of quality and VRAM usage.
- Can I run GPT OSS 20B ONNX on a Mac?
GPT OSS 20B ONNX requires at least 5.9 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 OSS 20B ONNX locally?
Yes — GPT OSS 20B ONNX can run locally on consumer hardware. At Q4_K_M quantization it needs 12.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GPT OSS 20B ONNX?
At Q4_K_M, GPT OSS 20B ONNX 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 Q4_K_M (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 GPT OSS 20B ONNX?
At Q4_K_M, the download is about 12.00 GB. The full-precision Q8_0 version is 20.00 GB. The smallest option (IQ2_XXS) is 5.50 GB.
- Which GPUs can run GPT OSS 20B ONNX?
17 consumer GPUs can run GPT OSS 20B ONNX at Q4_K_M (12.4 GB). Top options include AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, AMD Radeon RX 6800. 6 GPUs have plenty of headroom for comfortable inference.
- Which devices can run GPT OSS 20B ONNX?
27 devices with unified memory can run GPT OSS 20B ONNX at Q4_K_M (12.4 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.