Image-Text-to-Text
GGUF
rocmfpx
amd
vulkan
rocm
strix-halo
quantized
daisyrose
qwen3.8
imatrix
conversational
Instructions to use Harsha001/DaisyRose-27B-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 Harsha001/DaisyRose-27B-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 Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS # Run inference directly in the terminal: llama cli -hf Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS # Run inference directly in the terminal: llama cli -hf Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
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 Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS # Run inference directly in the terminal: ./build/bin/llama cli -hf Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
Use Docker
docker model run hf.co/Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
- Llama new
- LM Studio
- Jan
- vLLM
How to use Harsha001/DaisyRose-27B-ROCmFPX with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Harsha001/DaisyRose-27B-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": "Harsha001/DaisyRose-27B-ROCmFPX", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
- Ollama
How to use Harsha001/DaisyRose-27B-ROCmFPX with Ollama:
ollama run hf.co/Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
- Unsloth Desktop
- Pi
How to use Harsha001/DaisyRose-27B-ROCmFPX with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
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": "Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Harsha001/DaisyRose-27B-ROCmFPX with Docker Model Runner:
docker model run hf.co/Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
- Lemonade
How to use Harsha001/DaisyRose-27B-ROCmFPX with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
Run and chat with the model
lemonade run user.DaisyRose-27B-ROCmFPX-IQ2_XXS
List all available models
lemonade list
- Hermes Agent
How to use Harsha001/DaisyRose-27B-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 Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
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 Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Harsha001/DaisyRose-27B-ROCmFPX with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS
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 "Harsha001/DaisyRose-27B-ROCmFPX:IQ2_XXS" \ --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"
Model card
Browse files
README.md
CHANGED
|
@@ -21,19 +21,23 @@ attention every fourth layer, image input). The multi-token prediction layer of
|
|
| 21 |
|
| 22 |
| File | Size | Weights | Fits |
|
| 23 |
|---|---:|---|---|
|
| 24 |
-
| `DaisyRose-27B-Q8_0_ROCMFPX.gguf` |
|
| 25 |
-
| `DaisyRose-27B-Q6_0_ROCMFPX.gguf` |
|
| 26 |
-
| `DaisyRose-27B-Q4_0_ROCMFP4_STRIX_O8.gguf` |
|
| 27 |
| `mmproj-DaisyRose-27B-F16.gguf` | 0.9 GB | vision encoder, F16 | add for image input |
|
| 28 |
|
| 29 |
## Quality
|
| 30 |
|
| 31 |
-
KL divergence against the BF16 weights, 40 chunks of 512 tokens of English Wikipedia text (wikitext-2)
|
|
|
|
| 32 |
Lower is better. "Same top token" is how often the file's most likely next token matches BF16.
|
| 33 |
|
| 34 |
| Build | Size | Perplexity | KL to BF16 | Same top token |
|
| 35 |
|---|---:|---:|---:|---:|
|
| 36 |
-
| BF16 (reference, not published) | 54.6 GB |
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
Every file also passed a greedy chat check before upload ("What is the capital of France?" gives "Paris").
|
| 39 |
|
|
|
|
| 21 |
|
| 22 |
| File | Size | Weights | Fits |
|
| 23 |
|---|---:|---|---|
|
| 24 |
+
| `DaisyRose-27B-Q8_0_ROCMFPX.gguf` | 28.3 GB | 8-bit ROCmFPX, token embedding and output Q8_0 | Strix Halo, 32 GB AMD GPUs |
|
| 25 |
+
| `DaisyRose-27B-Q6_0_ROCMFPX.gguf` | 22.5 GB | 6-bit ROCmFPX, token embedding and output Q6_K | 24 GB AMD GPUs, Strix Halo |
|
| 26 |
+
| `DaisyRose-27B-Q4_0_ROCMFP4_STRIX_O8.gguf` | 19.2 GB | ROCmFP4, attention, delta net output and output layer 8-bit ROCmFPX | 16 to 24 GB AMD GPUs |
|
| 27 |
| `mmproj-DaisyRose-27B-F16.gguf` | 0.9 GB | vision encoder, F16 | add for image input |
|
| 28 |
|
| 29 |
## Quality
|
| 30 |
|
| 31 |
+
KL divergence against the BF16 weights, 40 chunks of 512 tokens of English Wikipedia text (wikitext-2). Each file was
|
| 32 |
+
expanded to F16 and scored on the same GPU backend as the BF16 reference, so the numbers show the weight format only.
|
| 33 |
Lower is better. "Same top token" is how often the file's most likely next token matches BF16.
|
| 34 |
|
| 35 |
| Build | Size | Perplexity | KL to BF16 | Same top token |
|
| 36 |
|---|---:|---:|---:|---:|
|
| 37 |
+
| BF16 (reference, not published) | 54.6 GB | 5.941 | | |
|
| 38 |
+
| **Q8_0_ROCMFPX** | 28.3 GB | 5.946 | 0.00025 | 99.3% |
|
| 39 |
+
| **Q6_0_ROCMFPX** | 22.5 GB | 5.947 | 0.0020 | 98.0% |
|
| 40 |
+
| **Q4_0_ROCMFP4_STRIX_O8** | 19.2 GB | 5.998 | 0.019 | 94.0% |
|
| 41 |
|
| 42 |
Every file also passed a greedy chat check before upload ("What is the capital of France?" gives "Paris").
|
| 43 |
|