Instructions to use kingjones777/LFM2.5-2.6B-DSpark-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 kingjones777/LFM2.5-2.6B-DSpark-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 kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16

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 kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16

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 kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16

Use Docker

docker model run hf.co/kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16

LM Studio
Jan

vLLM

How to use kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingjones777/LFM2.5-2.6B-DSpark-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": "kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16

Ollama
How to use kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF with Ollama:
```
ollama run hf.co/kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16
```

Unsloth Studio

How to use kingjones777/LFM2.5-2.6B-DSpark-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 kingjones777/LFM2.5-2.6B-DSpark-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 kingjones777/LFM2.5-2.6B-DSpark-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 kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF to start chatting

How to use kingjones777/LFM2.5-2.6B-DSpark-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 kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF with Docker Model Runner:
```
docker model run hf.co/kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16
```

Lemonade

How to use kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16

Run and chat with the model

lemonade run user.LFM2.5-2.6B-DSpark-ROCmFPX-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use kingjones777/LFM2.5-2.6B-DSpark-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 kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16

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 kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kingjones777/LFM2.5-2.6B-DSpark-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 kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16

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 "kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF:F16" \
  --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"

LFM2.5-2.6B-DSpark — DSpark draft, GGUF

GGUF conversion of the DSpark speculator for LiquidAI/LFM2.5-2.6B, for use with llama.cpp --spec-type draft-dspark. Paired target (ROCmFP4): kingjones777/LFM2.5-2.6B-ROCmFP4-COHERENT-GGUF.

⛔ READ THIS FIRST — measured SLOWER on AMD Strix Halo

We benchmarked this draft against its target and it reduced throughput. Published for completeness and reproducibility, not as a recommended speedup.

config	generation	effect
no drafter	103.1 t/s	—
`--spec-type draft-dspark --spec-draft-n-max 8`	83.4 t/s	-19.1%

Mean accepted length 2.58 (block size 9). AMD Ryzen AI Max+ 395 / Radeon 8060S (gfx1151), ROCm 7.13.0, idle box, median of 3, -ngl 999 -ngld 999 -fa on -c 2048 -n 512 --temp 0 --seed 1234. All three LFM2.5 sizes measured negative: −28.4% (1.2B), −19.1% (2.6B), −38.0% (8B-A1B).

Why — two runtime causes, not the weights

lfm2.cpp / lfm2moe.cpp do not populate t_layer_inp[], so draft-dspark aborts on GGML_ASSERT(t_layer_inp[il] != nullptr) out of the box. One-line fix: res->t_layer_inp[il] = prev_cur;
With that applied, llama.cpp reports recurrent state rollback is not compatible with 'draft-dspark' and falls back to a checkpoint path that is not bit-exact for LFM2's recurrent state — DSpark output diverges from greedy target output (reproducible 3/3).

An off-by-one in target-layer mapping was ruled out: LLAMA_DFLASH_TARGET_LAYER_OFFSET=-1 gave a worse accepted length (2.22), confirming the converter's +1 convention is correct.

On other stacks the same technique wins: DSpark measured +75% on Ling-3.0-flash under SGLang (22.3 → 39.1 t/s) on the same day. Speculative value belongs to the (model, runtime) pair.

Files

file	precision
`LFM2.5-2.6B-DSpark-F16.gguf`	F16
`LFM2.5-2.6B-DSpark-Q8_0.gguf`	Q8_0

No 4-bit draft is published: the draft's entire value is accepted length, and 4-bit would lower it further to save ~400 MB.

Requirements

llama.cpp with DSpark support (--spec-type draft-dspark), plus the t_layer_inp fix above for LFM2 targets. Converted with upstream llama.cpp e85caa81ea2b65797396018c179b87ad61fa38ab.

llama-cli -m <target>.gguf -md LFM2.5-2.6B-DSpark-F16.gguf \
  --spec-type draft-dspark --spec-draft-n-max 8 \
  -ngl 999 -ngld 999 -fa on

Provenance

Converted from LiquidAI/LFM2.5-2.6B-DSpark at revision 458cedab07d0f7b2b05700c77e1aa463d43d6f04. Licence inherited from the base model.

Downloads last month: 12

GGUF

Model size

0.3B params

Architecture

dflash

Hardware compatibility

8-bit

16-bit

Model tree for kingjones777/LFM2.5-2.6B-DSpark-ROCmFPX-GGUF

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

LiquidAI/LFM2.5-2.6B

Finetuned

LiquidAI/LFM2.5-2.6B-DSpark

Quantized

(2)

this model