OpenAI
GPT OSS 120B
- Weights at 16-bit
- 234 GB
- Weights at 8-bit (Q8_0)
- 124 GB
- Weights at 4-bit (Q4_K_M)
- 71 GB
- Smallest card at 4-bit
- More than one card
- Parameters
- Active parameters
- Layers
- KV heads
- Context
- Licence
Specs
- Active parameters
- Attention heads
- Context
- Downloads (30 days)
- Experts
- Experts per token
- Family
- GGUF downloads
-
repo bytes files quant ggml-org/gpt-oss-120b-GGUF 63,387,346,208 1 entries MXFP4 - Head size
- Hidden size
- KV heads
- Layers
- Licence
- Parameters
- Parameters by type
- Publisher
- Sliding window
- Sliding-window layers
- Task