Run unsloth/gpt-oss-20b-GGUF locally
unsloth/gpt-oss-20b-GGUF is a large language model with 20.91 billion parameters, built on the gpt-oss architecture. It is released under the apache-2.0 license and has been downloaded 352,246 times.
To run unsloth/gpt-oss-20b-GGUF locally at a 4,096-token context, its quantized versions need between 11.66 GB (Q3_K_S, lowest quality) and 13.83 GB (F16, highest quality) of memory, weights plus KV cache and a system margin included.
For most users the best balance is F16, needing about 13.83 GB. That means unsloth/gpt-oss-20b-GGUF fits entirely in the VRAM of a 12 GB GPU or larger, running fully on the GPU.
All quantizations
| Quant. | Bits | Quality | Weights | KV | Total | Speed~ | Verdict |
|---|---|---|---|---|---|---|---|
| Q3_K_S | 4.38 | Good | 10.68 GB | 0.19 GB | 11.66 GB | 4.7 t/s | Offload |
| Q2_K | 4.39 | Good | 10.68 GB | 0.19 GB | 11.67 GB | 4.7 t/s | Offload |
| Q4_0 | 4.4 | Good | 10.71 GB | 0.19 GB | 11.7 GB | 4.7 t/s | Offload |
| Q3_K_M | 4.4 | Good | 10.72 GB | 0.19 GB | 11.7 GB | 4.7 t/s | Offload |
| Q4_1 | 4.43 | Good | 10.78 GB | 0.19 GB | 11.77 GB | 4.6 t/s | Offload |
| Q4_K_S | 4.44 | Good | 10.82 GB | 0.19 GB | 11.81 GB | 4.6 t/s | Offload |
| Q4_K_M | 4.45 | Good | 10.83 GB | 0.19 GB | 11.81 GB | 4.6 t/s | Offload |
| Q5_K_S | 4.48 | Good | 10.91 GB | 0.19 GB | 11.89 GB | 4.6 t/s | Offload |
| Q5_K_M | 4.48 | Good | 10.91 GB | 0.19 GB | 11.9 GB | 4.6 t/s | Offload |
| Q2_K_L | 4.5 | Good | 10.95 GB | 0.19 GB | 11.94 GB | 4.6 t/s | Offload |
| Q4_K_XL | 4.54 | Good | 11.06 GB | 0.19 GB | 12.04 GB | 4.5 t/s | Offload |
| Q6_K | 4.61 | Good | 11.21 GB | 0.19 GB | 12.2 GB | 4.5 t/s | Offload |
| Q6_K_XL | 4.61 | Good | 11.21 GB | 0.19 GB | 12.2 GB | 4.5 t/s | Offload |
| Q8_0 | 4.63 | Good | 11.28 GB | 0.19 GB | 12.27 GB | 4.4 t/s | Offload |
| Q8_K_XL | 5.05 | Very good | 12.29 GB | 0.19 GB | 13.28 GB | 4.1 t/s | Offload |
| F16 | 5.28 | Very good | 12.85 GB | 0.19 GB | 13.83 GB | 3.9 t/s | Offload |
KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.
Frequently asked questions
How much VRAM do you need to run unsloth/gpt-oss-20b-GGUF?
You need about 11.94 GB of VRAM to run unsloth/gpt-oss-20b-GGUF entirely on the GPU using the Q2_K_L quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.
Can I run unsloth/gpt-oss-20b-GGUF on an 8 GB GPU?
Partially. unsloth/gpt-oss-20b-GGUF only fits on an 8 GB GPU by offloading part of it to system RAM (with F16), which runs but is slower.
Can I run unsloth/gpt-oss-20b-GGUF on a 16 GB GPU?
Yes. With 16 GB of VRAM you can run unsloth/gpt-oss-20b-GGUF fully on the GPU using F16 (about 13.83 GB).
Can I run unsloth/gpt-oss-20b-GGUF on a 24 GB GPU?
Yes. With 24 GB of VRAM you can run unsloth/gpt-oss-20b-GGUF fully on the GPU using F16 (about 13.83 GB).
What is the best quantization for unsloth/gpt-oss-20b-GGUF?
If memory allows, higher bits-per-weight means better quality. A common sweet spot is a Q4_K_M or Q5_K_M quantization, which keeps most of the quality while roughly halving the memory versus 8-bit. Pick the highest quantization that still fits in your VRAM.