Instructions to use singulared/Ornith-1.5-35B-ROCmFPX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use singulared/Ornith-1.5-35B-ROCmFPX-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 singulared/Ornith-1.5-35B-ROCmFPX-GGUF
# Run inference directly in the terminal:
llama cli -hf singulared/Ornith-1.5-35B-ROCmFPX-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf singulared/Ornith-1.5-35B-ROCmFPX-GGUF
# Run inference directly in the terminal:
llama cli -hf singulared/Ornith-1.5-35B-ROCmFPX-GGUF

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf singulared/Ornith-1.5-35B-ROCmFPX-GGUF
# Run inference directly in the terminal:
./llama-cli -hf singulared/Ornith-1.5-35B-ROCmFPX-GGUF

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf singulared/Ornith-1.5-35B-ROCmFPX-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf singulared/Ornith-1.5-35B-ROCmFPX-GGUF

Use Docker

docker model run hf.co/singulared/Ornith-1.5-35B-ROCmFPX-GGUF

LM Studio
Jan

vLLM

How to use singulared/Ornith-1.5-35B-ROCmFPX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "singulared/Ornith-1.5-35B-ROCmFPX-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "singulared/Ornith-1.5-35B-ROCmFPX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/singulared/Ornith-1.5-35B-ROCmFPX-GGUF

Ollama
How to use singulared/Ornith-1.5-35B-ROCmFPX-GGUF with Ollama:
```
ollama run hf.co/singulared/Ornith-1.5-35B-ROCmFPX-GGUF
```

Unsloth Studio

How to use singulared/Ornith-1.5-35B-ROCmFPX-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for singulared/Ornith-1.5-35B-ROCmFPX-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for singulared/Ornith-1.5-35B-ROCmFPX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for singulared/Ornith-1.5-35B-ROCmFPX-GGUF to start chatting

How to use singulared/Ornith-1.5-35B-ROCmFPX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf singulared/Ornith-1.5-35B-ROCmFPX-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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "singulared/Ornith-1.5-35B-ROCmFPX-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use singulared/Ornith-1.5-35B-ROCmFPX-GGUF with Docker Model Runner:
```
docker model run hf.co/singulared/Ornith-1.5-35B-ROCmFPX-GGUF
```

Lemonade

How to use singulared/Ornith-1.5-35B-ROCmFPX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull singulared/Ornith-1.5-35B-ROCmFPX-GGUF

Run and chat with the model

lemonade run user.Ornith-1.5-35B-ROCmFPX-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use singulared/Ornith-1.5-35B-ROCmFPX-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 singulared/Ornith-1.5-35B-ROCmFPX-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://127.0.0.1:8080/v1
hermes config set model.default singulared/Ornith-1.5-35B-ROCmFPX-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use singulared/Ornith-1.5-35B-ROCmFPX-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf singulared/Ornith-1.5-35B-ROCmFPX-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://127.0.0.1:8080/v1 \
  --custom-model-id "singulared/Ornith-1.5-35B-ROCmFPX-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"

Ornith-1.5-35B-ROCmFPX-GGUF / README.md

singulared

Generalise card: two variants, HYBRID and FAST

8c4f746 verified 4 days ago

preview code

Raw

History Blame Contribute Delete

5.14 kB

	---
	license: apache-2.0
	base_model:
	- ornith-ai/Ornith-1.5-35B-A3B
	base_model_relation: quantized
	library_name: llama.cpp
	pipeline_tag: text-generation
	tags:
	- gguf
	- rocm
	- rocmfpx
	- rocmfp4
	- rocmfp6
	- amd
	- strix-halo
	- gfx1151
	- mtp
	- speculative-decoding
	- moe
	---

	# Ornith-1.5-35B-A3B — ROCmFPX builds for Strix Halo

	ROCmFPX quantisations of [Ornith-1.5-35B-A3B](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B)
	for AMD Strix Halo (`gfx1151`), with the MTP head kept live for speculative decoding.

	\| file \| bpw \| size \| pick it for \|
	\| --- \| ---: \| ---: \| --- \|
	\| `Ornith-1.5-35B-HYBRID-fp6.gguf` \| 4.41 \| 18.21 GiB \| prefill-dominated work — best quality \|
	\| `Ornith-1.5-35B-ROCMFP4-FAST.gguf` \| 4.27 \| 17.65 GiB \| generation-dominated work — fastest decode \|

	More variants may be added later.

	## HYBRID: class-aware assignment

	Every stock ROCmFP4 preset leaves the obvious lever unused on a 256-expert MoE: they apply **one
	type to every tensor**. The hybrid splits them:

	\| tensor class \| count \| type \|
	\| --- \| ---: \| --- \|
	\| routed experts \| 123 \| `Q4_0_ROCMFP4_FAST` (4.25 bpw) \|
	\| attention \| 104 \| `Q6_0_ROCMFPX` (FP6) \|
	\| shared expert \| 123 \| `Q6_0_ROCMFPX` (FP6) \|
	\| token embedding / output \| 2 \| `Q6_0_ROCMFPX` (FP6) \|
	\| MTP (`nextn`) head \| 1 \| `Q4_0_ROCMFP4_FAST` \|

	4.41 bpw · 18.21 GiB. Routed experts are sparse (8 of 256 fire per token) and tolerate 4-bit;
	attention and the shared expert are on every token's critical path and get 6-bit.

	## Perplexity

	wikitext-2, 145 chunks @ ctx 2048, identical corpus, Vulkan, all measured here:

	\| build \| bpw \| size \| PPL \|
	\| --- \| ---: \| ---: \| --- \|
	\| HYBRID (this) \| 4.41 \| 18.21 GiB \| 7.3991 ±0.0506 \|
	\| `ROCMFP4_FAST` \| 4.27 \| 17.65 GiB \| 7.7749 ±0.0539 \|
	\| `ROCMFP4_COHERENT` \| 4.55 \| 18.81 GiB \| 7.8233 ±0.0550 \|
	\| `ROCMFP4_STRIX` \| 4.31 \| 17.81 GiB \| 7.8307 ±0.0547 \|

	The three stock presets cluster within 0.8% of each other — preset choice barely matters on this
	architecture, because none of them differentiate by tensor class. Class-aware assignment moves
	4.8% for +0.14 bpw.

	Perplexity measures prose next-token prediction, not agentic capability. Use it to compare
	quantisations of the same weights, not to rank models.

	## Speed (Radeon 8060S, gfx1151, Vulkan, MTP `n4`, `-ub 2048`)

	\| build \| 8.5K pp / tg \| 34K pp / tg \| 69K pp / tg \|
	\| --- \| --- \| --- \| --- \|
	\| HYBRID \| 990.9 / 63.0 \| 815.9 / 55.6 \| 488.4 / 45.2 \|
	\| `FAST` \| 993.9 / 87.7 \| 813.3 / 67.3 \| 478.9 / 56.3 \|

	Prefill is identical (within 0.5%) — it is compute-bound, so the FP6 weights cost nothing there.
	Decode pays the whole price: −28%, because FP6 attention means more bytes per generated token.

	⇒ Pick HYBRID for prefill-dominated work (digesting repos/documents, long context, short
	answers). Pick `FAST` for generation-dominated work. The recipe is a quality/decode dial, not a
	free win.

	Needle-in-a-haystack retrieval passes at 8.5K, 34.5K and 69.5K on both.

	## Backend: use Vulkan

	Same build, same model, same flags — only `-dev` changes:

	\| backend \| 8.5K pp / tg \| 34K pp / tg \|
	\| --- \| --- \| --- \|
	\| Vulkan \| 993.9 / 87.7 \| 813.3 / 67.3 \|
	\| HIP · ROCm 7.2.4 \| 968.1 / 72.7 \| 675.3 / 64.1 \|
	\| HIP · ROCm 10.1 nightly \| 1087.0 / 58.2 \| 834.6 / 55.1 \|

	The ROCm nightly is a prefill-for-decode trade: +12% prefill over HIP 7.2 but −20% decode, and
	−34% decode against Vulkan. Vulkan wins overall and needs no container.

	## MTP head at FP4 is safe here

	The `nextn.eh_proj` head is often kept at Q8_0 on the theory that it determines draft acceptance.
	Measured on this model, dropping it to FP4 did not hurt — identical perplexity to 4 decimals
	(7.7749 both) and slightly better acceptance:

	\| MTP head \| acceptance \|
	\| --- \| --- \|
	\| Q8_0 \| 0.73–0.77 \|
	\| FP4 \| 0.78–0.80 \|

	## Usage

	```bash
	llama-server -m Ornith-1.5-35B-HYBRID-fp6.gguf \
	-ngl 99 -c 131072 -dev Vulkan0 --jinja -fa on -b 2048 -ub 2048 \
	--spec-type draft-mtp --spec-draft-n-max 4 --spec-draft-p-min 0.6
	```

	Requires a [ROCmFPX](https://github.com/charlie12345/ROCmFPX) build — mainline llama.cpp does not
	know the `Q4_0_ROCMFP4_*` / `Q6_0_ROCMFPX` tensor types. The MTP head is native to Ornith 1.5
	(`blk.40.nextn.*`, `nextn_predict_layers=1`); no graft is needed, unlike 1.0.

	Reproduce the recipe with:

	```
	attn_.*=q6_0_rocmfpx
	ffn_(gate\|up\|down)_shexp=q6_0_rocmfpx
	token_embd.weight=q6_0_rocmfpx
	output.weight=q6_0_rocmfpx
	nextn.*=q4_0_rocmfp4_fast
	```
	`llama-quantize --tensor-type-file <rules> Ornith-1.5-35B-BF16.gguf out.gguf Q4_0_ROCMFP4_FAST`

	## Honest caveat

	On wikitext perplexity, Ornith 1.0 scores far better — 6.19 (ROCmFP4-COHERENT) against 7.40
	here, and the gap is present at BF16, so it is a property of the 1.5 weights and not of this
	quantisation. 1.0 also decodes faster (86.7 t/s) with higher draft acceptance (0.88).

	Ornith 1.5 is chosen here for its reported agentic/SWE gains, which wikitext does not measure. If
	your workload is prose modelling rather than agentic coding, 1.0 may serve you better.