GP

GPTOSS 120B Hanabi

GptossGGUF by mradermacherUpdated 2026-10-14
Download on Hugging Face
Parameters117B
Context128K
Layers36
Architecturegpt-oss
Smallest quant63.4 GB
Quick answer

GPTOSS 120B Hanabi needs about 89.0 GB of memory at Q4_K_M (a 87.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 12 quants, from 63.4 GB (MXFP4_MOE) to 124.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.

GPTOSS 120B Hanabi is a 117B-parameter Gptoss model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 12 quant files, from 63.4 GB (MXFP4_MOE) to 124.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE63.4 GB 64.5 GB
Too big Get file →
Q3_K_S66.1 GB 67.3 GB
Too big Get file →
Q2_K66.2 GB 67.3 GB
Too big Get file →
IQ4_XS67.0 GB 68.1 GB
Too big Get file →
Q3_K_M71.1 GB 72.2 GB
Too big Get file →
Q3_K_L73.4 GB 74.5 GB
Too big Get file →
Q4_K_S80.9 GB 82.0 GB
Too big Get file →
Q4_K_M87.9 GB 89.0 GB
Too big Get file →
Q5_K_S88.0 GB 89.1 GB
Too big Get file →
Q5_K_M93.9 GB 95.0 GB
Too big Get file →
Q6_K124.2 GB 125.3 GB
Too big Get file →
Q8_0124.3 GB 125.4 GB
Too big Get file →

What GPU do you need for GPTOSS 120B Hanabi?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which GPTOSS 120B Hanabi quant should you choose?

Q4_K_M is the usual starting point for GPTOSS 120B Hanabi: it balances file size and quality well. Here it is a 87.9 GB file.

The Q8_0 file is 124.3 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is MXFP4_MOE at 63.4 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters117B (approximate, mixture of experts)
Layers36
Trained context131,072 tokens
KV cache (fp16)72 KB per token

Source

Quantized bymradermacher
FamilyGptoss
Downloads (HF)548
Last updated2026-10-14

Frequently asked questions about GPTOSS 120B Hanabi

How much VRAM does GPTOSS 120B Hanabi need?

About 89.0 GB at Q4_K_M with an 8K context window. That is the 87.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run GPTOSS 120B Hanabi on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 64.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GPTOSS 120B Hanabi GGUF?

It depends on the quant: MXFP4_MOE is 63.4 GB, Q3_K_S is 66.1 GB, Q2_K is 66.2 GB, IQ4_XS is 67.0 GB, Q3_K_M is 71.1 GB, Q3_K_L is 73.4 GB and 6 more.

What context length does GPTOSS 120B Hanabi support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.

Where can I download GPTOSS 120B Hanabi GGUF?

The files are on Hugging Face in the mradermacher/GPTOSS-120B-Hanabi-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gptoss models

All Gptoss →

Other large models

All large models →