openai_gpt-oss-120b GGUF size and VRAM requirements
bartowski/openai_gpt-oss-120b-GGUF is a very large language model with 116.83 billion parameters, built on the gpt-oss architecture. It has been downloaded 26,703 times.
To run bartowski/openai_gpt-oss-120b-GGUF locally at a 4,096-token context, its quantized versions need between 59.3 GB (Q3_K_L, lowest quality) and 61.88 GB (BF16, highest quality) of memory, weights plus KV cache and a system margin included.
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 | Quality | Weights | KV | Total | Speed~ | Verdict |
|---|---|---|---|---|---|---|---|
| Q3_K_L | 4.29 | Good | 58.3 GB | 0.2 GB | 59.3 GB | — | Insufficient |
| Q4_0 | 4.29 | Good | 58.34 GB | 0.2 GB | 59.34 GB | — | Insufficient |
| IQ2_M | 4.29 | Good | 58.38 GB | 0.2 GB | 59.38 GB | — | Insufficient |
| Q3_K_S | 4.29 | Good | 58.39 GB | 0.2 GB | 59.39 GB | — | Insufficient |
| IQ3_M | 4.29 | Good | 58.4 GB | 0.2 GB | 59.4 GB | — | Insufficient |
| Q2_K | 4.29 | Good | 58.4 GB | 0.2 GB | 59.4 GB | — | Insufficient |
| Q3_K_M | 4.29 | Good | 58.4 GB | 0.2 GB | 59.4 GB | — | Insufficient |
| IQ4_NL | 4.29 | Good | 58.4 GB | 0.2 GB | 59.4 GB | — | Insufficient |
| IQ4_XS | 4.29 | Good | 58.4 GB | 0.2 GB | 59.4 GB | — | Insufficient |
| Q4_1 | 4.3 | Good | 58.43 GB | 0.2 GB | 59.43 GB | — | Insufficient |
| Q4_K_M | 4.3 | Good | 58.53 GB | 0.2 GB | 59.52 GB | — | Insufficient |
| Q3_K_XL | 4.31 | Good | 58.57 GB | 0.2 GB | 59.57 GB | — | Insufficient |
| Q2_K_L | 4.31 | Good | 58.67 GB | 0.2 GB | 59.67 GB | — | Insufficient |
| Q4_K_L | 4.32 | Good | 58.73 GB | 0.2 GB | 59.73 GB | — | Insufficient |
| Q6_K | 4.33 | Good | 58.94 GB | 0.2 GB | 59.94 GB | — | Insufficient |
| Q8_0 | 4.34 | Good | 59.03 GB | 0.2 GB | 60.03 GB | — | Insufficient |
| GGUF | 4.35 | Good | 59.18 GB | 0.2 GB | 60.18 GB | — | Insufficient |
| BF16 | 4.48 | Good | 60.88 GB | 0.2 GB | 61.88 GB | — | Insufficient |
KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.
Frequently asked questions
Can I run bartowski/openai_gpt-oss-120b-GGUF on an 8 GB GPU?
No. bartowski/openai_gpt-oss-120b-GGUF does not fit on an 8 GB GPU, even with the smallest quantization and system RAM offloading.
Can I run bartowski/openai_gpt-oss-120b-GGUF on a 16 GB GPU?
No. bartowski/openai_gpt-oss-120b-GGUF does not fit on a 16 GB GPU, even with the smallest quantization and system RAM offloading.
Can I run bartowski/openai_gpt-oss-120b-GGUF on a 24 GB GPU?
Partially. bartowski/openai_gpt-oss-120b-GGUF only fits on a 24 GB GPU by offloading part of it to system RAM (with BF16), which runs but is slower.
What is the best quantization for bartowski/openai_gpt-oss-120b-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.