Text Generation
GGUF
English
llama.cpp
rocmfpx
rocm
amd
strix-halo
gfx1151
mtp
speculative-decoding
agent
tool-use
code
qwen3
vision
imatrix
conversational
Instructions to use philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX 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 philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX 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 philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16 # Run inference directly in the terminal: llama cli -hf philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16 # Run inference directly in the terminal: llama cli -hf philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
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 philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
Use Docker
docker model run hf.co/philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
- Llama new
- LM Studio
- Jan
- vLLM
How to use philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
- Ollama
How to use philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX with Ollama:
ollama run hf.co/philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
- Unsloth Desktop
- Pi
How to use philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
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": "philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX with Docker Model Runner:
docker model run hf.co/philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
- Lemonade
How to use philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
Run and chat with the model
lemonade run user.Qwopus3.6-27B-Coder-MTP-ROCmFPX-BF16
List all available models
lemonade list
- Hermes Agent
How to use philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
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 philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16
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 "philtheriver/Qwopus3.6-27B-Coder-MTP-ROCmFPX:BF16" \ --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"
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model:
|
| 4 |
-
- Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF
|
| 5 |
base_model_relation: quantized
|
| 6 |
pipeline_tag: text-generation
|
| 7 |
library_name: llama.cpp
|
|
@@ -27,8 +26,8 @@ tags:
|
|
| 27 |
|
| 28 |
A **ROCmFPX** quantization of [`Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF`](https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF) built for **AMD Strix Halo** (Ryzen AI MAX, `gfx1151`, 128 GB unified). 27B dense, Apache-2.0, MTP head intact (`draft=2`), agent/tool-use tuned, multimodal (Qwen3-VL).
|
| 29 |
|
| 30 |
-
> ⚠️ **Requires the [ROCmFPX llama.cpp fork](https://github.com/charlie12345/ROCmFPX).**
|
| 31 |
-
> `ROCmFPX` is a family of **custom AMD quant types**
|
| 32 |
|
| 33 |
> ℹ️ **The Hugging Face precision badge is wrong.** HF's GGUF parser can't read ROCmFPX block layouts and will mislabel this (e.g. "F16"). Pick the file by **filename**; the real footprint is **~6.5 bpw** (+ f16 token embeddings + Q6_K output head).
|
| 34 |
|
|
@@ -61,7 +60,7 @@ llama-quantize \
|
|
| 61 |
|
| 62 |
## Quant tiers (see the **Files** tab)
|
| 63 |
|
| 64 |
-
Every tier carries the MTP head (`draft=2`) and pairs with the bundled `mmproj-F32.gguf` (vision).
|
| 65 |
f16 token embeddings throughout; `_AGENT` presets route attn/FFN at higher precision for tool-call /
|
| 66 |
JSON coherence. Filenames are prefixed `Qwopus3.6-27B-Coder-MTP-STRIX-`.
|
| 67 |
|
|
@@ -79,8 +78,9 @@ JSON coherence. Filenames are prefixed `Qwopus3.6-27B-Coder-MTP-STRIX-`.
|
|
| 79 |
## Running (ROCmFPX fork required)
|
| 80 |
|
| 81 |
```bash
|
| 82 |
-
# 1) build the fork
|
| 83 |
git clone https://github.com/charlie12345/ROCmFPX.git && cd ROCmFPX
|
|
|
|
| 84 |
JOBS=16 scripts/build-strix-rocmfp4-mtp.sh # -> build-strix-rocmfp4/bin/
|
| 85 |
|
| 86 |
# 2) serve with MTP speculative decoding + vision
|
|
@@ -90,12 +90,12 @@ build-strix-rocmfp4/bin/llama-server \
|
|
| 90 |
--alias qwopus-coder \
|
| 91 |
-dev ROCm0 -ngl 999 -fa on -c 32768 \
|
| 92 |
--spec-type draft-mtp --spec-draft-ngl all --spec-draft-n-max 2 \
|
| 93 |
-
--jinja --mmproj mmproj-F32.gguf \
|
| 94 |
--host 0.0.0.0 --port 8080
|
| 95 |
```
|
| 96 |
|
| 97 |
- **MTP:** the head is built in (`draft=2`). Run with `--spec-type draft-mtp`; `--spec-draft-n-max 2` was optimal in testing.
|
| 98 |
-
- **Vision (Qwen3-VL):** bundled `mmproj-F32.gguf`; pass `--mmproj` (add `--image-min-tokens 1024` for high-detail images).
|
| 99 |
- **Tool calls:** point your client at the **`qwen3_coder`** tool-call parser, or the model narrates code instead of emitting structured calls.
|
| 100 |
- The chat template is embedded — `--jinja` reads it.
|
| 101 |
|
|
@@ -130,7 +130,7 @@ build-strix-rocmfp4/bin/llama-server \
|
|
| 130 |
|
| 131 |
- **Prompt processing ~30% faster than stock `Q6_K`** (despite the larger file) — the gfx1151-tuned ROCmFPX kernels win the compute-bound prefill; a real payoff for long-context / agentic workloads.
|
| 132 |
- **Decode (`tg`) is bandwidth-bound** — ≈ `Q6_K` at equal size; the format doesn't change it. ¹ Raw decode — **MTP (`--spec-type draft-mtp`) roughly doubles it** in serving.
|
| 133 |
-
-
|
| 134 |
|
| 135 |
## Credits & license
|
| 136 |
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF
|
|
|
|
| 4 |
base_model_relation: quantized
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
library_name: llama.cpp
|
|
|
|
| 26 |
|
| 27 |
A **ROCmFPX** quantization of [`Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF`](https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF) built for **AMD Strix Halo** (Ryzen AI MAX, `gfx1151`, 128 GB unified). 27B dense, Apache-2.0, MTP head intact (`draft=2`), agent/tool-use tuned, multimodal (Qwen3-VL).
|
| 28 |
|
| 29 |
+
> ⚠️ **Requires the [ROCmFPX llama.cpp fork](https://github.com/charlie12345/ROCmFPX), built at commit [`553504b`](https://github.com/charlie12345/ROCmFPX/commit/553504bd5d16fe1374e9b1508a1f395c9a35d746).**
|
| 30 |
+
> `ROCmFPX` is a family of **custom AMD quant types**; this build uses **enum IDs 110–115**. Those IDs are **not upstream-stable** — a newer fork revision could renumber them and silently mis-decode these weights, so **build from the pinned commit above**. The file will **NOT load** in stock `llama.cpp`, LM Studio, Ollama, or any other runtime — only the fork's `llama-quantize`/`llama-server` understand it.
|
| 31 |
|
| 32 |
> ℹ️ **The Hugging Face precision badge is wrong.** HF's GGUF parser can't read ROCmFPX block layouts and will mislabel this (e.g. "F16"). Pick the file by **filename**; the real footprint is **~6.5 bpw** (+ f16 token embeddings + Q6_K output head).
|
| 33 |
|
|
|
|
| 60 |
|
| 61 |
## Quant tiers (see the **Files** tab)
|
| 62 |
|
| 63 |
+
Every tier carries the MTP head (`draft=2`) and pairs with the bundled `mmproj/mmproj-F32.gguf` (vision).
|
| 64 |
f16 token embeddings throughout; `_AGENT` presets route attn/FFN at higher precision for tool-call /
|
| 65 |
JSON coherence. Filenames are prefixed `Qwopus3.6-27B-Coder-MTP-STRIX-`.
|
| 66 |
|
|
|
|
| 78 |
## Running (ROCmFPX fork required)
|
| 79 |
|
| 80 |
```bash
|
| 81 |
+
# 1) build the fork at the pinned commit (ROCm/HIP toolchain, gfx1151)
|
| 82 |
git clone https://github.com/charlie12345/ROCmFPX.git && cd ROCmFPX
|
| 83 |
+
git checkout 553504b # enum IDs 110-115 match this revision
|
| 84 |
JOBS=16 scripts/build-strix-rocmfp4-mtp.sh # -> build-strix-rocmfp4/bin/
|
| 85 |
|
| 86 |
# 2) serve with MTP speculative decoding + vision
|
|
|
|
| 90 |
--alias qwopus-coder \
|
| 91 |
-dev ROCm0 -ngl 999 -fa on -c 32768 \
|
| 92 |
--spec-type draft-mtp --spec-draft-ngl all --spec-draft-n-max 2 \
|
| 93 |
+
--jinja --mmproj mmproj/mmproj-F32.gguf \
|
| 94 |
--host 0.0.0.0 --port 8080
|
| 95 |
```
|
| 96 |
|
| 97 |
- **MTP:** the head is built in (`draft=2`). Run with `--spec-type draft-mtp`; `--spec-draft-n-max 2` was optimal in testing.
|
| 98 |
+
- **Vision (Qwen3-VL):** bundled `mmproj/mmproj-F32.gguf`; pass `--mmproj` (add `--image-min-tokens 1024` for high-detail images).
|
| 99 |
- **Tool calls:** point your client at the **`qwen3_coder`** tool-call parser, or the model narrates code instead of emitting structured calls.
|
| 100 |
- The chat template is embedded — `--jinja` reads it.
|
| 101 |
|
|
|
|
| 130 |
|
| 131 |
- **Prompt processing ~30% faster than stock `Q6_K`** (despite the larger file) — the gfx1151-tuned ROCmFPX kernels win the compute-bound prefill; a real payoff for long-context / agentic workloads.
|
| 132 |
- **Decode (`tg`) is bandwidth-bound** — ≈ `Q6_K` at equal size; the format doesn't change it. ¹ Raw decode — **MTP (`--spec-type draft-mtp`) roughly doubles it** in serving.
|
| 133 |
+
- Measured on **this** (Coder) build. The FP4 row is the v2 STRIX_LEAN — the only 4-bit on hand — as a bit-width reference.
|
| 134 |
|
| 135 |
## Credits & license
|
| 136 |
|