license: apache-2.0
base_model: meta-models/Muse-Glimmer-30B
base_model_relation: quantized
tags:

• gguf
• llama.cpp
• rocm
• amd
• rocmfp4
• rocmfpx
• strix-halo
• gfx1151
• uncensored
• abliterated
• dflash
• speculative-decoding
  pipeline_tag: image-text-to-text

Muse-Glimmer-30B Uncensored — ROCmFP4 for AMD Strix Halo (gfx1151)

Uncensored ROCmFP4 quantisations of meta-models/Muse-Glimmer-30B, built with the same ROCmFPX pipeline and the same card ftypes as kingjones777/Muse-Glimmer-30B-ROCmFP4-Strix-Halo-DFlash-GGUF.

Research artifact. Abliteration removes content-refusal. It does not add capability. Do not ship this as a product default. The aligned repo remains the serving default.

Why this build?

The aligned card measured STRIX_LEAN (106) at 18.72 tok/s and FAST (103) at 20.31 tok/s in a controlled A/B (DFlash n=15, ctx 32K, -fa on). This repo is those same ftypes from an abliterated checkpoint, plus the Q6 AGENT/LEAN pair.

Q6 LEAN (ftype 116) is not the card LEAN. Card LEAN = 106.

Which file should I use?

Start with STRIX_LEAN (106) if you want the card-matched LEAN. Take FAST (103) if you want the aligned speed pick. Take Q6 AGENT (114) if you want more bits and will live with ~Q6 decode.

Ryzen AI Max+ 395, ROCm 7.2.4, DFlash --spec-draft-n-max 15, -fa on, ctx 32768, batch 1, temperature 0. Warm medians of 3; first call after load discarded.

Same flags, same drafter as the aligned card. Decode on this model is workload-dominated — quote a range, not a point.

Quick start

llama-server \
  -m muse-glimmer-30B-Uncensored-ROCmFP4-STRIX_LEAN.gguf \
  --spec-type draft-dflash --model-draft dflash-kquant.gguf \
  --spec-draft-n-max 15 --spec-draft-ngl 99 --spec-draft-device ROCm0 \
  --chat-template-kwargs '{"reasoning_strength":"low"}' \
  -ngl 999 -fa on -dio --jinja -fit off -dev ROCm0 -c 32768 \
  --host 127.0.0.1 --port 8080

Requires a llama.cpp built with ROCmFP4 (ggml types 100–106) and the muse-glimmer port. Stock llama.cpp rejects these tensor types.

--reasoning-budget is not enforced on this model. Use reasoning_strength.

Uncensored findings

Content-refusal scoring on a 24 harmful / 12 harmless / 8 quality research set, greedy (temp 0). Counts only — no payloads. Abliteration is supposed to drop harmful-tune refusals without wrecking ordinary Q&A.

Reading:

• Aligned Qwen still refuses almost everything on this set. Abliterated Qwen complies on almost everything. Quality score is identical (same two fails: Márquez needle + bat-and-ball).
• Aligned Muse is leakier than aligned Qwen on this classifier — a few complies even before abliteration.
• Quality is a substring smoke check, not MMLU. It is a regression guard against a broken quant, not a capability claim.

Files

Six files. llama.cpp loads them via --model, --model-draft and --mmproj. This repo is the uncensored family only — aligned builds are a separate repo.

Quantization

PYTHONPATH=gguf-py python convert_hf_to_gguf.py <MODEL_DIR> --outtype bf16 --outfile unc-BF16.gguf
llama-quantize unc-BF16.gguf …-FAST.gguf Q4_0_ROCMFP4_FAST 16
llama-quantize unc-BF16.gguf …-STRIX_LEAN.gguf Q4_0_ROCMFP4_STRIX_LEAN 16

No extra --tensor flags — matches the published aligned card. ROCmFPX llama-quantize only.

Known issues (same as aligned)

1. Vulkan/CUDA/CPU cannot load these files — ROCmFP4 is ROCm-only.
2. Vision requires -fa off.
3. Small max_tokens returns empty content — budget goes to reasoning_content.
4. --reasoning-budget is not enforced; use reasoning_strength.
5. This is an uncensored research build. Do not deploy it as the public default.

Not yet measured

License and attribution

Base model: Meta Muse-Glimmer-30B (Apache 2.0). ROCmFP4 types: ROCmFPX. This repository is quantisation and measurement of an abliterated Muse-Glimmer-30B checkpoint.

See the aligned card for the muse-glimmer architecture port, DFlash notes, and tool-calling suite.