gpt-oss-20b-Derestricted GGUF size and VRAM requirements

⬇ 46,862 ❤ 2
Parameters20.91B
Context131,072

MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF is a large language model with 20.91 billion parameters, built on the gpt-oss architecture. It has been downloaded 46,862 times.

To run MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF locally at a 4,096-token context, its quantized versions need between 12.17 GB (Q2_K, lowest quality) and 39.92 GB (GGUF, highest quality) of memory, weights plus KV cache and a system margin included.

For most users the best balance is Q6_K, needing about 21.6 GB. That means MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF fits entirely in the VRAM of a 16 GB GPU or larger, running fully on the GPU.

→ Guide: How much VRAM do you need?

GGUF file size and memory by quantization

Compare real GGUF weight sizes, estimated KV cache and total memory for Q4, Q5, Q8 and every quantization published in this repository.

Quant.Bits QualityWeights KVTotal Speed~Verdict
Q2_K 4.62 Good 11.24 GB 0.13 GB 12.17 GB 4.4 t/s Offload
Q3_K_M 4.94 Good 12.03 GB 0.13 GB 12.96 GB 4.2 t/s Offload
Q3_K_L 5.1 Very good 12.42 GB 0.13 GB 13.35 GB 4.0 t/s Offload
Q4_K_M 6.05 Very good 14.72 GB 0.13 GB 15.65 GB 3.4 t/s Offload
Q5_K_M 6.46 Very good 15.73 GB 0.13 GB 16.66 GB 3.2 t/s Offload
Q6_K 8.49 Excellent 20.67 GB 0.13 GB 21.6 GB 2.4 t/s Offload
GGUF 16.01 Excellent 38.99 GB 0.13 GB 39.92 GB Insufficient

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 MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF?

You need about 15.65 GB of VRAM to run MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF entirely on the GPU using the Q4_K_M quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.

Can I run MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF on an 8 GB GPU?

Partially. MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF only fits on an 8 GB GPU by offloading part of it to system RAM (with Q6_K), which runs but is slower.

Can I run MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF on a 16 GB GPU?

Yes. With 16 GB of VRAM you can run MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF fully on the GPU using Q4_K_M (about 15.65 GB).

Can I run MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF on a 24 GB GPU?

Yes. With 24 GB of VRAM you can run MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF fully on the GPU using Q6_K (about 21.6 GB).

What is the best quantization for MaziyarPanahi/gpt-oss-20b-Derestricted-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.