---

license: apache-2.0

pipeline_tag: text-generation

base_model:

• openai/gpt-oss-120b

tags:

• gguf
• quantized
• mxfp4
• moe
• siliang-engine
• experimental

---

gpt-oss-120b MXFP4 - Siliang Expert-Major Repack

This is an experimental repack of

ggml-org/gpt-oss-120b-GGUF,

derived from OpenAI's

gpt-oss-120b, for

Siliang Engine.

The GPT-OSS neural architecture and MXFP4 quantization are unchanged. The

modification is a Siliang-specific expert-major GGUF storage layout and

metadata extension for routed Mixture-of-Experts weights. No fine-tuning or

additional quantization pass was performed.

> [!IMPORTANT]

> This file is not a general-purpose GGUF. It requires Siliang Engine v0.1.1

> or a compatible build that understands the siliangem.* metadata contract.

> Plain upstream llama.cpp and other GGUF applications do not understand the

> packed expert-major tensors.

Modification notice

This repository redistributes modified model material. The source MXFP4 GGUF's

routed-expert weights were physically rearranged into Siliang's expert-major

layout. The model architecture, expert IDs, tokenizer metadata, and intended

model behavior were not deliberately changed by the repack.

What the repack changes

Stock MoE GGUFs store each routed-expert projection as a tensor spanning all

experts. This repack instead places the projections for each expert together:

[expert 0: gate | up | down][expert 1: gate | up | down] ...

Each layer is represented by one packed region. Siliang Engine reconstructs

the original logical gate, up, and down tensors from the embedded geometry.

This lets one arena miss fetch an expert with one sector-aligned contiguous

read rather than separate scattered projection reads.

The layout is designed to reduce fragmented read submissions, reduce reliance

on Windows mmap page faults for routed-expert weights, and lower effective

expert-fetch latency. It does not guarantee lower total bytes read, fewer

system-wide page faults, or a specific speedup. Results depend on storage,

available RAM, memory pressure, routing behavior, and arena sizing.

Compatibility

• Engine: Siliang Engine v0.1.1

or a compatible later build.

• Accelerated runtime: Windows. Linux support is not available in the current

experimental release.

• Memory mapping must remain enabled. Siliang deliberately rejects this layout

with --no-mmap because its logical expert tensors are strided views.

• Arena acceleration is opt-in. Without a positive SILIANGEM_CACHE_MIB,

Siliang uses its mmap path and does not reserve an arena.

• GPT-OSS requires the Harmony response format. Use a chat interface or

conversation mode that applies the model's GPT-OSS chat template; raw

unformatted prompts are not equivalent.

Quickstart

Download and extract a Siliang Engine v0.1.1 Windows release. From its root,

choose an arena budget measured for your machine and leave enough memory for

Windows, non-expert weights, the KV cache, and GPU shared-memory pressure:

.\scripts\siliang-env.ps1 -CacheMiB <measured-MiB>

& ".\bin\llama-cli.exe" `
    -m "<path>\gpt-oss-120b-MXFP4-MoE-siliang-expert-major.gguf" `
    -cnv

.\scripts\siliang-env.ps1 -Reset

Larger arenas are not automatically better. Do not treat the 18 GiB benchmark

configuration below as a safe default for another machine.

Artifact details

| Field | Value |

| --- | --- |

| File | gpt-oss-120b-MXFP4-MoE-siliang-expert-major.gguf |

| Size | 63,397,407,232 bytes (59.043437 GiB) |

| GGUF | Version 3, 512-byte alignment |

| Model architecture | gpt-oss |

| Routed-expert type | MXFP4 |

| MoE geometry | 36 layers, 128 experts per layer, 4 selected per token |

| Packed layout | 36 tensors, gate | up | down per expert |

| Expert stride | 13,221,376 bytes |

| Metadata namespace | Nine siliangem. keys; no retired behemoth. keys |

Validation

From a Siliang Engine v0.1.1 checkout, run the structural checker:

python .\scripts\check_expert_major.py `
    --model "<path>\gpt-oss-120b-MXFP4-MoE-siliang-expert-major.gguf"

The expected result includes:

{
  "alignment": 512,
  "expertCount": 128,
  "layerCount": 36,
  "partNames": ["gate", "up", "down"],
  "partTypeIds": [39],
  "status": "expert-major-metadata-ok"
}

This artifact passes that check. A deterministic current-namespace smoke also

produced identical 32-token decoded output with the arena disabled and enabled;

the arena armed without an mmap fallback. That smoke established structural

and runtime-path correctness only. Its timings were intentionally excluded.

A structural pass does not prove semantic equivalence to the source model or

replace an application-specific correctness test.

Performance evidence

The retained GPT-OSS benchmark compares the same repacked GGUF through two

Siliang paths. It does not compare a stock GGUF with this repack.

| Path | Median decode | Observed range |

| --- | ---: | ---: |

| Repacked GGUF using mmap | 1.972 tok/s | 1.964-2.030 tok/s |

| Same GGUF using an 18 GiB deferred arena | 4.052 tok/s | 3.953-4.094 tok/s |

This was a historical matched run with three fresh process starts per arm, a

48-token warmup, and 256 measured tokens. The median arena change was +105.5%

(2.06x). It isolates the arena and deferred direct-I/O path on one repacked

file; it does not measure the repack's benefit against stock GPT-OSS. Complete

model and runtime composite hashes were not retained for this historical run,

so it is not current release-validation evidence.

The test system used Windows 11, an AMD Ryzen 5 2600, 24 GB of RAM, an NVIDIA

GeForce RTX 2070 with 8 GB of VRAM, and a WD_BLACK SN850X NVMe SSD operating

through a PCIe 3.0 x4 platform link. The 18 GiB arena created high memory

pressure on this system. These measurements are experimental system-specific

evidence, not a general performance guarantee. Full methodology and caveats

are in the

Siliang Engine performance notes.

No retained GPT-OSS control currently demonstrates fewer total disk bytes,

fewer operating-system page faults, or the isolated stock-versus-repack

effect. No bit-for-bit whole-file equivalence claim is made.

Source, license, and attribution

• Base model: openai/gpt-oss-120b
• Source GGUF lineage: ggml-org/gpt-oss-120b-GGUF,

gpt-oss-120b-MXFP4.gguf

• Runtime: SpeederX/siliang-engine
• Original model card and citation: OpenAI's GPT-OSS model card
• Usage policy: OpenAI GPT-OSS Usage Policy

The model material is distributed under the Apache License 2.0. The complete

license text is included in LICENSE. Review the upstream model

card for capabilities, safety evaluations, intended use, and broader model

limitations.