---

license: apache-2.0

base_model: openai/gpt-oss-120b

base_model_relation: quantized

pipeline_tag: text-generation

library_name: gguf

tags:

- gguf

- rocmfp4

- quantized

- imatrix

- amd

- rocm

- strix-halo

- moe

- gpt-oss

---

GPT-OSS-120B — ROCmFP4 STRIX_LEAN for AMD Strix Halo

ROCmFP4 GGUF requantization of openai/gpt-oss-120b (117B MoE, 5.1B active), produced for AMD Strix Halo (Ryzen AI Max, gfx1151).

To our knowledge the first ROCmFP4-family quant of gpt-oss. +21% decode over the native MXFP4 release on Strix Halo at essentially identical size — the gain is pure kernel efficiency (the ROCmFP4 layout streams at near-peak bandwidth on gfx1151).

> ⚠️ Stock llama.cpp will reject this file (invalid ggml type 106). It runs on:

> - the kyuz0/amd-strix-halo-toolboxes rocm-7.2.4-rocmfp4 container image, or

> - the Hal0ai/Hal0_ROCmFPX llama.cpp fork.

Companion repos: Qwen3.6-35B-A3B · Nemotron-3-Nano-30B · Ornith-1.0-35B · Ornith-1.0-9B

Files

| File | Quant | BPW | Size |

|---|---|---|---|

| gpt-oss-120b-Q4_0_ROCMFP4_STRIX_LEAN.gguf | Q4_0_ROCMFP4_STRIX_LEAN | ~4.25 | 62.4 GB |

Measured performance

AMD Ryzen AI Max+ 395 (Strix Halo, 128 GB unified LPDDR5X, ROCm, llama-bench -fa 1 --mmap 0):

| Quant | Size | pp512 | tg128 |

|---|---|---|---|

| Q4_0_ROCMFP4_STRIX_LEAN | 58.1 GiB | 593 | 61.7 |

| native MXFP4 (ggml-org) | 59.0 GiB | 587 | 50.9 |

Provenance & quality disclosure

Requantized from the native MXFP4 release (no BF16 master exists for gpt-oss) with llama-quantize --allow-requantize, calibrated with bartowski's imatrix. FP4→FP4 regridding adds rounding noise; on an 8-prompt quality battery vs the native release (temp 0), 7/8 answers were byte-equivalent-or-equal-quality and one contained a minor arithmetic slip in an illustrative example (the substantive answer remained correct). Judge that trade for your workload — the native MXFP4 remains available from ggml-org.

Serving

llama-server -m gpt-oss-120b-Q4_0_ROCMFP4_STRIX_LEAN.gguf \
  -ngl 999 -fa on --jinja -c 65536

Credits

• Base model: OpenAI — gpt-oss-120b (Apache-2.0)
• imatrix: bartowski
• ROCmFP4 quant formats: Hal0ai; GPU quantizer build: kyuz0