---

license: other

license_name: qwen-community-1.0

base_model:

- orcarouter/Qwen3.8-Flash-Next-Uncensored

- Qwen/Qwen3.8-Flash-Next

base_model_relation: quantized

pipeline_tag: text-generation

library_name: gguf

tags:

- gguf

- rocmfp4

- llama.cpp

- strix-halo

- gfx1151

- rocm

- amd

- ryzen-ai-max

- uncensored

- research

---

> ### 🔧 Runtime: build the ROCmFPX fork below

> Stock llama.cpp will not load this file. You need both the qwen4exp architecture

> and the ROCmFP4 tensor types in one tree. Upstream

> charlie12345/ROCmFPX has the ROCmFP4 types but

> not qwen4exp. Our fork has both:

>

> kingjones30/ROCmFPX — a fork of charlie12345/ROCmFPX, branch main.

>

> ```bash

> git clone https://github.com/kingjones30/ROCmFPX.git

> cd ROCmFPX

> cmake -B build -DGGML_HIP=ON -DGPU_TARGETS=gfx1151 -DGGML_NATIVE=ON -DCMAKE_BUILD_TYPE=Release

> cmake --build build --target llama-server llama-quantize -j$(nproc)

> ```

>

> Verified 2026-08-27 on gfx1151: clean clone → 0 build errors → llama-server loads a

> qwen4exp ROCmFP4 GGUF from this family and generates coherent text.

Qwen3.8-Flash-Next-Uncensored — ROCmFP4 FAST GGUF — AMD Ryzen AI Max+ 395 / gfx1151

⚠️ Research artifact. Refusal behaviour has been removed. This does not add capability — it

removes guardrails. Use it deliberately, in a context where that is appropriate, and own the output.

> ### ⛔ ngram-mod at ≥64K can wedge the GPU

>

> --spec-type ngram-mod is the right spec-decode for this family on ROCm, and it is fine at 32K.

> At 64K and above, a context-checkpoint restore desyncs the QSA indexer cache from the KV

> caches. The next kernel then wedges the SDMA queue — Ring sdma0 reset failure, D-state

> llama-server, kill -9 useless, hard power-off to recover. Field report by

> @liusecret on

> Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF#6.

>

> Workaround (no new binary required):

> ```

> -ctxcp 0 -cpent -1

> ```

> --ctx-checkpoints 0 plus --checkpoint-every-n-tokens -1. If no checkpoints are created,

> the restore path never runs. Keep ngram-mod on ROCm; do not use it on Vulkan/gfx1151

> (acceptance collapses to 0). A fork that serialises mem_idx is the real fix — until that

> binary is in your hands, use the flags.

Quantized from the BF16 weights published by

orcarouter/Qwen3.8-Flash-Next-Uncensored

— the abliteration work here is theirs, not mine. Go star their repo.

FAST is the smallest tier and the one to take if you are disk-constrained: the

Q4_0_ROCMFP4_FAST recipe — attention, experts, token embeddings and the PLE table all ROCmFP4,

with only the output head lifted to Q6_K.

Converted to BF16 GGUF and quantized by me from their release. 4.27 bpw, 87.94 GiB.

| tensor group | type |

|---|---|

| MoE expert weights (ffn_*_exps) | TYPE_101 (ROCmFP4, 4.251 bpw) |

| shared expert (ffn_*_shexp) | TYPE_101 |

| attention (attn_*) | all TYPE_101 |

| per_layer_token_embd.weight (PLE, 51.2B params) | TYPE_101 |

| token_embd.weight | TYPE_101 |

| output.weight (lm head) | Q6_K |

The size matches my aligned build of the same tier to 0.01 GiB — the abliterated checkpoint is

structurally identical, so the quant recipe transfers exactly.

The Q6_K head

output.weight is Q6_K, never 4-bit. Every sampled token passes through the lm head, so its

quantization error lands directly in the argmax. Verified by exact tensor name after both

quantize and split — output.weight is a substring of attn_output.weight, so a loose check

reports success on a 4-bit head.

Building a runtime that loads these files

Needs two things in one tree: the qwen4exp architecture and the ROCmFP4 tensor types.

charlie12345/ROCmFPX has the ROCmFP4 types but not qwen4exp; the upstream qwen4exp work has no

ROCmFP4. The patch combining them ships in this repo:

qwen4exp-on-rocmfpx-d3ca537.patch (156 KB, 25 files).

git clone https://github.com/charlie12345/ROCmFPX.git
cd ROCmFPX && git checkout d3ca537
curl -LO https://huggingface.co/kingjones777/Qwen3.8-Flash-Next-Uncensored-ROCmFP4-STRIX_LEAN-GGUF/resolve/main/qwen4exp-on-rocmfpx-d3ca537.patch
git apply qwen4exp-on-rocmfpx-d3ca537.patch
cmake -B build -DGGML_HIP=ON -DGPU_TARGETS=gfx1151 -DGGML_NATIVE=ON -DCMAKE_BUILD_TYPE=Release
cmake --build build --target llama-server llama-quantize -j$(nproc)

Verified from a clean clone: applies without conflicts, compiles with zero errors, and the built

llama-server loads these GGUFs and generates. The patch's new files —

src/llama-memory-hybrid-idx.{cpp,h} (the QSA indexer's own memory class),

src/models/qwen4exp.cpp, conversion/qwen4exp.py — are the pieces hand-copying misses.

Measured — Ryzen AI MAX+ 395, gfx1151, ROCm 7.2.4, full 49/49 offload

• generation: 22.75 tok/s
• prompt processing: 387.3 tok/s
• GPU memory: 63.3 GiB resident — identical to the aligned build

GPU-only, full offload. I do not publish partial-offload speeds.

*Measured with one fixed 6,963-token prompt reused across samples (cache_prompt: false), run 1

discarded as warm-up, median of the 4 settled samples — spread 1.6 tok/s. An earlier figure of

222 tok/s came from a flawed method that used a different corpus slice per sample; that injected

slice-to-slice variance straight into the number. Same file, same GTT (63.6 GiB) — only the

measurement changed.*

Long context

This model's native max is 262,144, and it runs there on a 128 GB box:

| context | prompt | pp tok/s | gen tok/s | GTT |

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

| 131,072 | 111,411 | 196 | 15.22 | 69.1 GiB |

| 262,144 | 8,000 | 307 | 22.48 | 72.0 GiB |

| 262,144 | 200,000 | 128 | 10.46 | 74.9 GiB |

The context window is nearly free — GTT grows only ~4 GiB from 8k to 128k, because Qwen Sparse

Attention caps KV. What you pay for is depth: a 200k-token prompt halves generation. It

degrades smoothly rather than falling off a cliff.

Refusal / quality (counts only)

Aligned build vs this one, same prompts, greedy, same harness:

| split | aligned | this build |

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

| Harmful (24) | 0 comply | 22 comply |

| Harmless (12) | 10 ok | 11 ok |

| Quality (8) | 6/8 | 6/8 — same two failures |

Quality is unchanged to the specific failing question, which is the point: the abliteration

flipped refusal without the quant damaging the model. Prompts and completions are not published.

Files

Sharded to stay under HF's 50 GB limit. Point --model at the first shard.

| file | size |

|---|---|

| Qwen3.8-Flash-Next-Uncensored-Q4_0-ROCmFP4-FAST-00001-of-00003.gguf | 41.63 GiB |

| Qwen3.8-Flash-Next-Uncensored-Q4_0-ROCmFP4-FAST-00002-of-00003.gguf | 41.60 GiB |

| Qwen3.8-Flash-Next-Uncensored-Q4_0-ROCmFP4-FAST-00003-of-00003.gguf | 4.71 GiB |

| mmproj-Qwen3.8-Flash-Next-Uncensored-BF16.gguf | 0.85 GiB (vision tower) |

Usage

llama-server \
  --model Qwen3.8-Flash-Next-Uncensored-Q4_0-ROCmFP4-FAST-00001-of-00003.gguf \
  --mmproj mmproj-Qwen3.8-Flash-Next-Uncensored-BF16.gguf \
  --host 127.0.0.1 --port 8080 \
  --n-gpu-layers 999 --flash-attn on --fit off \
  --ctx-size 131072 --threads 16 --jinja

Do not use --no-mmap. The PLE table is streamed from the file through the page cache; forcing

it into anonymous memory gets the process OOM-killed with nothing in the server log.

<!-- CREDITS:START -->

Acknowledgements

charlie12345/ROCmFPX — defines the ROCmFP4 tensor

formats. Every file here was produced with its llama-quantize and runs on its runtime. MIT, based

on upstream llama.cpp. The qwen4exp architecture is not part of that fork — it comes from

upstream llama.cpp work and is applied on top via

qwen4exp-on-rocmfpx-d3ca537.patch in this repo.

llama.cpp — ggml-org and contributors — the engine,

GGUF format and conversion tooling this is built on.

AMD ROCm — the compute platform targeted here (ROCm 7.2.4, gfx1151).

orcarouter — published the uncensored BF16 checkpoint

this is built from. The abliteration is their engineering; I only converted and quantized it.

Qwen team — the original base model. See base_model; license qwen-community-1.0.

<!-- CREDITS:END -->