Text Generation
GGUF
English
llama.cpp
bitnet
ternary
1.58-bit
quantized
q4_k_m
edge
efficient-inference
cpu
tool-calling
Instructions to use Qapdex/SLM750-Edge-1.58-bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Qapdex/SLM750-Edge-1.58-bit with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Qapdex/SLM750-Edge-1.58-bit", filename="quantized_q4km.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Qapdex/SLM750-Edge-1.58-bit 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 Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT # Run inference directly in the terminal: llama cli -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT # Run inference directly in the terminal: llama cli -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
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 Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT # Run inference directly in the terminal: ./llama-cli -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
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 Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT # Run inference directly in the terminal: ./build/bin/llama-cli -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
Use Docker
docker model run hf.co/Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
- LM Studio
- Jan
- vLLM
How to use Qapdex/SLM750-Edge-1.58-bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qapdex/SLM750-Edge-1.58-bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qapdex/SLM750-Edge-1.58-bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
- Ollama
How to use Qapdex/SLM750-Edge-1.58-bit with Ollama:
ollama run hf.co/Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
- Unsloth Studio
How to use Qapdex/SLM750-Edge-1.58-bit 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 Qapdex/SLM750-Edge-1.58-bit 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 Qapdex/SLM750-Edge-1.58-bit to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Qapdex/SLM750-Edge-1.58-bit to start chatting
- Atomic Chat new
- Docker Model Runner
How to use Qapdex/SLM750-Edge-1.58-bit with Docker Model Runner:
docker model run hf.co/Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
- Lemonade
How to use Qapdex/SLM750-Edge-1.58-bit with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
Run and chat with the model
lemonade run user.SLM750-Edge-1.58-bit-Q4_K_M_QUANT
List all available models
lemonade list
| set -euo pipefail | |
| export LD_LIBRARY_PATH=/data/data/com.termux/files/usr/lib/python3.13/site-packages/lib:/data/data/com.termux/files/usr/lib:$LD_LIBRARY_PATH | |
| # Usage: ./bitnet_benchmark.sh /pfad/zum/model.gguf | |
| VK_ICD_FILENAMES="$PREFIX/share/vulkan/icd.d/freedreno_icd.aarch64.json" | |
| KMP_AFFINITY="disabled" | |
| EXECUTABLE_DISABLE_MTE="1" | |
| MODEL="${1:-models/quantized_q4km.gguf}" | |
| PROMPT="${2:-Hallo BitNet}" | |
| MAX_TOKENS="${3:-64}" | |
| WARMUPS="${4:-3}" | |
| RUNS="${5:-5}" | |
| THREADS="${6:-$(nproc)}" | |
| N_CTX="${7:-512}" | |
| LOGDIR="${HOME}/bitnet_benchmark_logs" | |
| mkdir -p "$LOGDIR" | |
| echo "Model: $MODEL" | |
| echo "Prompt: $PROMPT" | |
| echo "Max new tokens: $MAX_TOKENS" | |
| echo "Warmups: $WARMUPS, Runs: $RUNS, Threads: $THREADS, n_ctx: $N_CTX" | |
| echo "Logs: $LOGDIR" | |
| echo | |
| # Helper to run inference and measure seconds | |
| run_once() { | |
| local outlog="$1" | |
| local start end elapsed | |
| start=$(date +%s.%N) | |
| python3 ~/BitNet/run_inference.py -m "$MODEL" -t "$THREADS" \ | |
| -c "$N_CTX" -n "$MAX_TOKENS" -p "$PROMPT" --no-stream \ | |
| >"$outlog" 2>&1 || true | |
| end=$(date +%s.%N) | |
| elapsed=$(echo "$end - $start" | bc -l) | |
| printf "%.6f\n" "$elapsed" | |
| } | |
| # 1) Measure cold load + first token (single run) | |
| echo "Measuring cold load + first token..." | |
| COLDLOG="$LOGDIR/cold_run.log" | |
| cold_time=$(run_once "$COLDLOG") | |
| echo "Cold run time: $cold_time s" | |
| echo | |
| # 2) Warmups | |
| echo "Warmup runs ($WARMUPS)..." | |
| for i in $(seq 1 $WARMUPS); do | |
| wlog="$LOGDIR/warmup_${i}.log" | |
| t=$(run_once "$wlog") | |
| echo " Warmup $i: ${t}s" | |
| done | |
| echo | |
| # 3) Timed runs | |
| echo "Timed runs ($RUNS)..." | |
| times_file="$LOGDIR/times.txt" | |
| : > "$times_file" | |
| for i in $(seq 1 $RUNS); do | |
| rlog="$LOGDIR/run_${i}.log" | |
| t=$(run_once "$rlog") | |
| echo "$t" | tee -a "$times_file" | |
| echo " Run $i: ${t}s" | |
| done | |
| # 4) Stats | |
| python3 - <<PY | |
| import statistics,sys | |
| times = [float(x.strip()) for x in open("$times_file") if x.strip()] | |
| if not times: | |
| print("No timed runs recorded") | |
| sys.exit(1) | |
| median = statistics.median(times) | |
| mean = statistics.mean(times) | |
| minv = min(times) | |
| maxv = max(times) | |
| tokens = $MAX_TOKENS | |
| print("---- Summary ----") | |
| print(f"Runs: {len(times)}") | |
| print(f"Median time per run: {median:.4f} s") | |
| print(f"Mean time per run: {mean:.4f} s") | |
| print(f"Min: {minv:.4f} s Max: {maxv:.4f} s") | |
| print(f"Tokens generated per run: {tokens}") | |
| print(f"Tokens per second (median): {tokens/median:.2f}") | |
| print(f"Tokens per second (mean): {tokens/mean:.2f}") | |
| PY | |
| echo | |
| echo "Detaillogs liegen in $LOGDIR" | |
| echo "Fertig" | |