Instructions to use ubergarm/Step-3.5-Flash-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 ubergarm/Step-3.5-Flash-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 ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

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 ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

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 ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

Use Docker

docker model run hf.co/ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

LM Studio
Jan

vLLM

How to use ubergarm/Step-3.5-Flash-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ubergarm/Step-3.5-Flash-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": "ubergarm/Step-3.5-Flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

Ollama
How to use ubergarm/Step-3.5-Flash-GGUF with Ollama:
```
ollama run hf.co/ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
```

Unsloth Studio

How to use ubergarm/Step-3.5-Flash-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 ubergarm/Step-3.5-Flash-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 ubergarm/Step-3.5-Flash-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ubergarm/Step-3.5-Flash-GGUF to start chatting

How to use ubergarm/Step-3.5-Flash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

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": "ubergarm/Step-3.5-Flash-GGUF:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ubergarm/Step-3.5-Flash-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 ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

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 ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ubergarm/Step-3.5-Flash-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

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 "ubergarm/Step-3.5-Flash-GGUF:IQ4_XS" \
  --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"

Docker Model Runner
How to use ubergarm/Step-3.5-Flash-GGUF with Docker Model Runner:
```
docker model run hf.co/ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
```

Lemonade

How to use ubergarm/Step-3.5-Flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

Run and chat with the model

lemonade run user.Step-3.5-Flash-GGUF-IQ4_XS

List all available models

lemonade list

Ot parameters

by theracn - opened Feb 8

Discussion

theracn

Feb 8

im very impressed with the double speed between lamacpp and iklama, and the model here and the official gguf one they uploaded, my question since im a bit greedy and would like more than the 5.6t/s im getting can i get more by precise tensors allocations? thats my begining log, i have 3x 3090, 1x 4070ti 1 on 16x, rest on 4x pcie lanes and i have 96 RAM DDR4 and i7 13700k processor.

D:\iklama\ik_llama.cpp\build\bin\Release>llama-server.exe ^
More? --model "D:\models\step35\Step-3.5-Flash-IQ4_XS-00001-of-00004.gguf" ^
More? --alias ubergarm/GLM-4.7 ^
More? --ctx-size 8536 ^
More? -sm graph ^
More? -smgs ^
More? -mea 256 ^
More? -ngl 99 ^
More? --n-cpu-moe 60 ^
More? -ts 13,29,29,29 ^
More? -ub 512 -b 512 ^
More? --threads 24 ^
More? --parallel 1 ^
More? --host 127.0.0.1 ^
More? --port 8085 ^
More? --no-mmap ^
More? --jinja
INFO [ main] build info | tid="27984" timestamp=1770520791 build=4189 commit="e22b2d12"
INFO [ main] system info | tid="27984" timestamp=1770520791 n_threads=24 n_threads_batch=-1 total_threads=24 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | "
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 4 CUDA devices:
Device 0: NVIDIA GeForce RTX 4070 Ti, compute capability 8.9, VMM: yes, VRAM: 12281 MiB
Device 1: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes, VRAM: 24575 MiB
Device 2: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes, VRAM: 24575 MiB
Device 3: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes, VRAM: 24575 MiB
CUDA0: using device CUDA0 - 11036 MiB free
CUDA1: using device CUDA1 - 23304 MiB free
CUDA2: using device CUDA2 - 23304 MiB free
CUDA3: using device CUDA3 - 23304 MiB free

Hunterx

Feb 8

Cant you play with these perams? just decrease --n-cpu-moe until you have no more vram available.

-ngl 99
--n-cpu-moe 54

ubergarm

Owner Feb 8

Yeah take some time to dial in your system, here are some things to read:

gist covering how it works: https://gist.github.com/DocShotgun/a02a4c0c0a57e43ff4f038b46ca66ae0
-sm graph you're already using, and if a model is supported for that on ik it is the fastest way to run GGUFs anywhere on multi GPU rigs

Since you're already using -sm graph you might be able to play around with the ordering of the GPUs passing env vars and using -mg 0 to set the main gpu to the fastest/most pcie lanes...

more advanced stuff includes changing the reduce operation quantization type and other things, but that is beyond me given i mainly use CPU rig and don't experiment that much with >2 GPUs.

Read up on the closed PRs on ik_llama.cpp or join some discussions over on the beaver ai discord: https://huggingface.co/BeaverAI

ubergarm

Owner Feb 8

Also if you can use -ub 4096 -b 4096 (keep in mind the default values are -ub 512 -b 2048` you can probably get more PP

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment