GGUF
English
rocmfp4
qwen3next
qwen3-coder-next
coder
Mixture of Experts
imatrix
strix-halo
amd
rocm
vulkan
conversational
Instructions to use plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF # Run inference directly in the terminal: llama cli -hf plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF # Run inference directly in the terminal: llama cli -hf plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF # Run inference directly in the terminal: ./build/bin/llama cli -hf plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF
Use Docker
docker model run hf.co/plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF
- Llama new
- LM Studio
- Jan
- Ollama
How to use plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF with Ollama:
ollama run hf.co/plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF
- Unsloth Desktop
- Pi
How to use plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF with Docker Model Runner:
docker model run hf.co/plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF
- Lemonade
How to use plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF
Run and chat with the model
lemonade run user.Qwen3-Coder-Next-ROCmFP4-GGUF-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "plunderstruck/Qwen3-Coder-Next-ROCmFP4-GGUF" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Add card: Qwen3-Coder-Next ROCmFP4 (Q8 emb, code-weighted imatrix); measured -20% median KL on held-out code
Browse files
README.md
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-Coder-Next
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
library_name: gguf
|
| 5 |
+
tags:
|
| 6 |
+
- gguf
|
| 7 |
+
- rocmfp4
|
| 8 |
+
- qwen3next
|
| 9 |
+
- qwen3-coder-next
|
| 10 |
+
- coder
|
| 11 |
+
- moe
|
| 12 |
+
- imatrix
|
| 13 |
+
- strix-halo
|
| 14 |
+
- amd
|
| 15 |
+
- rocm
|
| 16 |
+
- vulkan
|
| 17 |
+
language:
|
| 18 |
+
- en
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
# Qwen3-Coder-Next β ROCmFP4 STRIX (Q8 embeddings, imatrix)
|
| 22 |
+
|
| 23 |
+
Experimental **AMD Strix Halo (gfx1151)** quant of [**Qwen3-Coder-Next**](https://huggingface.co/Qwen/Qwen3-Coder-Next)
|
| 24 |
+
β Qwen's agentic coding model (80B total / **3B active** high-sparsity MoE, hybrid Gated-DeltaNet attention,
|
| 25 |
+
262K context) β in the custom **ROCmFP4** 4-bit format, **imatrix-quantized** with a code-weighted
|
| 26 |
+
importance matrix.
|
| 27 |
+
|
| 28 |
+
> **β οΈ Ignore HuggingFace's auto-detected quant badge ("F16"/16-bit) β it's wrong.**
|
| 29 |
+
> HF can't read the custom ROCmFP4 tensor types and mislabels the file. **These are ~4.5 bpw 4-bit
|
| 30 |
+
> ROCmFP4 files, not 16-bit.** Pick by filename in *Files and versions*.
|
| 31 |
+
|
| 32 |
+
> ## Requires the ROCmFP4 fork (public) β not stock llama.cpp
|
| 33 |
+
> Uses the **ROCmFP4** tensor types (`q4_0_rocmfp4`, `q4_0_rocmfp4_fast`). **Stock llama.cpp, LM Studio,
|
| 34 |
+
> Ollama, etc. cannot load it.** Build/run with
|
| 35 |
+
> **[`charlie12345/rocmfp4-llama`](https://github.com/charlie12345/rocmfp4-llama)** (`mtp-rocmfp4-strix`).
|
| 36 |
+
|
| 37 |
+
## Why this is a great fit for a single APU
|
| 38 |
+
|
| 39 |
+
- **Fast even without speculative decoding.** 3B active params + linear Gated-DeltaNet attention β
|
| 40 |
+
**~54 t/s** short-context decode on a Ryzen AI Max+ 395 (Vulkan0), and cheap long context (DeltaNet's
|
| 41 |
+
near-constant memory). No MTP needed.
|
| 42 |
+
- **Note on MTP:** Qwen3-Coder-Next ships **without** an MTP head, and the ROCmFP4 fork currently wires
|
| 43 |
+
MTP drafting only for the `qwen35`/`qwen35moe` archs, **not** `qwen3next`. So these are **no-MTP** builds.
|
| 44 |
+
In practice it doesn't matter much β it's already ~2Γ the decode speed of the 27B/40B MTP models.
|
| 45 |
+
|
| 46 |
+
## Two files (pick your trade-off)
|
| 47 |
+
|
| 48 |
+
Both share the same 4-bit ROCmFP4 body, **Q8 embeddings**, and the code-weighted imatrix. They differ only
|
| 49 |
+
in the **output head**:
|
| 50 |
+
|
| 51 |
+
| File | output head | best for |
|
| 52 |
+
|---|---|---|
|
| 53 |
+
| `β¦-STRIX-embQ8-imatrix.gguf` | 4-bit | **fastest** β recommended default |
|
| 54 |
+
| `β¦-STRIX-embQ8-imatrix-headQ6.gguf` | **Q6_K** | a notch more faithful output, ~5β7% slower decode |
|
| 55 |
+
|
| 56 |
+
- **Q8 embeddings** (not f16): the source is Q8_0, so Q8 matches its precision exactly β f16 would be
|
| 57 |
+
fake-f16 bloat for zero gain (embeddings are a lookup, not a matmul).
|
| 58 |
+
- **MoE experts + attention/SSM projections** β 4-bit ROCmFP4; the DeltaNet-specific tensors
|
| 59 |
+
(`ssm_conv1d`, `ssm_a`, norms, router) stay **F32**.
|
| 60 |
+
|
| 61 |
+
## The imatrix β code-weighted, and measured
|
| 62 |
+
|
| 63 |
+
Quantized **with an importance matrix** built from a **code-weighted** calibration mix (~2.6:1 code:general):
|
| 64 |
+
- **Code:** real multi-language source + code-analysis prompts, sampled from
|
| 65 |
+
[`eaddario/imatrix-calibration`](https://huggingface.co/datasets/eaddario/imatrix-calibration).
|
| 66 |
+
- **General:** Kalomaze's `groups_merged` (via [`froggeric/imatrix`](https://huggingface.co/datasets/froggeric/imatrix)).
|
| 67 |
+
|
| 68 |
+
*(Note on "dual imatrix": a plain merge of two imatrices is mathematically identical to concatenating the
|
| 69 |
+
corpora at the same ratio β the only real lever is the code:general ratio, which is what's set here. True
|
| 70 |
+
size-decoupled balancing would need normalized-merge tooling; not used.)*
|
| 71 |
+
|
| 72 |
+
**Measured benefit** β KL-divergence + perplexity vs the **Q8 reference** on a **held-out code** slice
|
| 73 |
+
(disjoint from calibration), imatrix vs no-imatrix:
|
| 74 |
+
|
| 75 |
+
| metric (vs Q8, held-out code) | no-imatrix | **imatrix** | change |
|
| 76 |
+
|---|---|---|---|
|
| 77 |
+
| **Median KLD** | 0.00597 | **0.00478** | **β20%** |
|
| 78 |
+
| 90th-pct KLD | 0.1342 | 0.1083 | β19% |
|
| 79 |
+
| **RMS Ξp** | 8.14% | **7.36%** | β10% |
|
| 80 |
+
| **Same top token as Q8** | 91.01% | **91.49%** | +0.48 pp |
|
| 81 |
+
| Mean PPL | 3.4556 | 3.4686 | +0.013 (within Β±0.077 noise β a wash) |
|
| 82 |
+
|
| 83 |
+
So the imatrix **measurably improves quantization fidelity to the full model on code** (median KL β20%,
|
| 84 |
+
the gold-standard metric), at **zero cost** (same size/speed). PPL is a statistical wash. Honest scope:
|
| 85 |
+
this is a fidelity-vs-Q8 measurement on ~20 K tokens of held-out code, **not** an absolute coding benchmark.
|
| 86 |
+
|
| 87 |
+
## How it was built (reproducible)
|
| 88 |
+
|
| 89 |
+
```bash
|
| 90 |
+
# code-weighted imatrix on the Q8 (single pass; ratio = the real lever)
|
| 91 |
+
llama-imatrix -m Qwen3-Coder-Next-Q8_0.gguf -f code-weighted-calib.txt -o coder-next.imatrix -c 512 -ngl 999
|
| 92 |
+
|
| 93 |
+
# quant -> ROCmFP4 with the imatrix (Q8 embeddings). headQ6 adds --output-tensor-type q6_K
|
| 94 |
+
llama-quantize --allow-requantize --token-embedding-type q8_0 --imatrix coder-next.imatrix \
|
| 95 |
+
Qwen3-Coder-Next-Q8_0.gguf Qwen3-Coder-Next-ROCmFP4-STRIX-embQ8-imatrix.gguf Q4_0_ROCMFP4_STRIX
|
| 96 |
+
```
|
| 97 |
+
|
| 98 |
+
## Usage
|
| 99 |
+
|
| 100 |
+
```bash
|
| 101 |
+
env HSA_OVERRIDE_GFX_VERSION=11.5.1 GGML_HIP_ENABLE_UNIFIED_MEMORY=1 \
|
| 102 |
+
llama-server -m Qwen3-Coder-Next-ROCmFP4-STRIX-embQ8-imatrix.gguf \
|
| 103 |
+
--alias qwen3-coder-next-rocmfp4 --host 0.0.0.0 --port 8080 \
|
| 104 |
+
-dev Vulkan0 -ngl 999 -fa on -c 131072 -b 2048 -ub 256 -t 16 -tb 16 \
|
| 105 |
+
-ctk f16 -ctv f16 --cache-reuse 256 \
|
| 106 |
+
--temp 0.7 --top-p 0.8 --top-k 20 --jinja --parallel 1 --metrics --no-mmap
|
| 107 |
+
```
|
| 108 |
+
|
| 109 |
+
(No `--spec-type draft-mtp` β this arch has no MTP head; it's fast on its own.)
|
| 110 |
+
|
| 111 |
+
## Credits & license
|
| 112 |
+
|
| 113 |
+
- **Model:** [`Qwen/Qwen3-Coder-Next`](https://huggingface.co/Qwen/Qwen3-Coder-Next) (Apache-2.0, Qwen team) β a derivative quantization; verify the base terms before redistribution/use.
|
| 114 |
+
- **Calibration:** [`eaddario/imatrix-calibration`](https://huggingface.co/datasets/eaddario/imatrix-calibration) (code), Kalomaze `groups_merged` via [`froggeric/imatrix`](https://huggingface.co/datasets/froggeric/imatrix) (general).
|
| 115 |
+
- **ROCmFP4 format & runtime:** [`charlie12345/rocmfp4-llama`](https://github.com/charlie12345/rocmfp4-llama) (based on llama.cpp, MIT).
|