Instructions to use prithivMLmods/Thinklite-27B-NVFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prithivMLmods/Thinklite-27B-NVFP4-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="prithivMLmods/Thinklite-27B-NVFP4-GGUF")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("prithivMLmods/Thinklite-27B-NVFP4-GGUF", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use prithivMLmods/Thinklite-27B-NVFP4-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 prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4 # Run inference directly in the terminal: llama cli -hf prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4 # Run inference directly in the terminal: llama cli -hf prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
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 prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4 # Run inference directly in the terminal: ./build/bin/llama cli -hf prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
Use Docker
docker model run hf.co/prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
- Llama new
- LM Studio
- Jan
- vLLM
How to use prithivMLmods/Thinklite-27B-NVFP4-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "prithivMLmods/Thinklite-27B-NVFP4-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": "prithivMLmods/Thinklite-27B-NVFP4-GGUF", "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/prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
- SGLang
How to use prithivMLmods/Thinklite-27B-NVFP4-GGUF with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "prithivMLmods/Thinklite-27B-NVFP4-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prithivMLmods/Thinklite-27B-NVFP4-GGUF", "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 images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "prithivMLmods/Thinklite-27B-NVFP4-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prithivMLmods/Thinklite-27B-NVFP4-GGUF", "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" } } ] } ] }' - Ollama
How to use prithivMLmods/Thinklite-27B-NVFP4-GGUF with Ollama:
ollama run hf.co/prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
- Unsloth Desktop
- Pi
How to use prithivMLmods/Thinklite-27B-NVFP4-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
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": "prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use prithivMLmods/Thinklite-27B-NVFP4-GGUF with Docker Model Runner:
docker model run hf.co/prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
- Lemonade
How to use prithivMLmods/Thinklite-27B-NVFP4-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
Run and chat with the model
lemonade run user.Thinklite-27B-NVFP4-GGUF-NVFP4
List all available models
lemonade list
- Hermes Agent
How to use prithivMLmods/Thinklite-27B-NVFP4-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 prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
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 prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use prithivMLmods/Thinklite-27B-NVFP4-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4
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 "prithivMLmods/Thinklite-27B-NVFP4-GGUF:NVFP4" \ --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"
Thinklite-27B-NVFP4-GGUF
Thinklite-27B is a fine-tune of Qwen3.8-27B (Apache-2.0, image-text-to-text) that is trained on the base model's own verified-correct answers so it reaches the same results with shorter reasoning. Only the thinking is shortened, and the final answer keeps its normal length and format. It is a drop-in replacement with the same chat template, tokenizer, and
reasoning_effortcontrol (low,medium,xhigh). On the authors' six-benchmark suite (GSM8K, AIME 2025, MMLU-Pro, IFEval, LiveCodeBench v6, BFCL v4), it uses about 47% fewer reasoning tokens atxhighand about 28% fewer atlow. Atxhighit keeps 99.6% of the base model's average accuracy (89.8 vs 90.2), and atlowit keeps 97.5% (84.7 vs 86.9). Atxhigh, time-to-final-output is roughly 2x faster, since decoding speed is unchanged. It also beats two comparable efficiency fine-tunes, ThinkingCap and Swift-1.5, on token savings, but those two score higher on average accuracy in the authors' own tables. Its vision encoder is unchanged and its training data was text-only. A small 88-question check suggests image understanding is preserved, with 24% fewer reasoning tokens. The card's limitations include lower accuracy on IFEval and MMLU-Pro atxhigh, a larger drop on AIME 2025 atlow(81.7 vs 90.0), weaker reliability on long single-answer code generation, wide confidence intervals from single benchmark runs, and no safety tuning beyond the base model. It is served with vLLM or Transformers, and a 16.5 GB Q4_K_M GGUF is available for llama.cpp and Ollama.
MTP β Speculative Decoding: Yes | Accelerated FP4 Tensor Core Performance
Multi-Token Prediction (MTP) GGUF is a specialized GGUF model file format extension that integrates speculative decoding directly into the model weights to significantly accelerate local inference. Unlike traditional speculative decoding which requires a separate, smaller "draft" model, MTP GGUF files include additional output heads within the main model architecture that predict multiple future tokens in a single forward pass.
Model Files
| File Name | Quant Type | File Size | File Link | Description |
|---|---|---|---|---|
| Thinklite-27B-NVFP4.gguf | NVFP4 | 33.1 GB | Link | NVFP4 quantization. Highly optimized for NVIDIA Blackwell hardware accelerators (e.g., RTX Pro 6000, RTX 50-series, B200, B300), offering native hardware-accelerated FP4 Tensor Core speeds and a strong balance of size and performance for this 27B parameter model. |
| Thinklite-27B.mmproj.gguf | mmproj | 931 MB | Link | Multimodal projection file. Used for vision/language capabilities. |
NVFP4 Test Run
Tested Thinklite-27B-NVFP4.gguf on an NVIDIA RTX PRO 6000 Blackwell Server Edition GPU with 96 GB of VRAM, using llama-cli with full GPU offloading and MTP speculative decoding.
Performance Metrics
| Metric | Value |
|---|---|
| Average Prompt Processing Speed | 267.66 tokens/s |
| Average Generation Speed | 83.61 tokens/s |
| Total Wall Time | 73.9 seconds |
| Context Length | 16,384 tokens |
| KV Cache (K) | q8_0 |
| GPU | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| GPU VRAM Capacity | 96 GB |
| Peak GPU VRAM Usage | 30.98 GiB |
| Peak GPU Utilization | 97% |
| GPU Layers Offloaded | 99 (-ngl 99) |
| Random Seed | 42 |
| Speculative Decoding | MTP (draft_n_max=2) |
| Test Runs | 5 |
Test Shots
| Shot | Test |
|---|---|
| Shot 1 | C: Insert Node at End of Singly Linked List |
| Shot 2 | Jogger and Train Passing Time |
| Shot 3 | Two Pipes Filling a Tank |
| Shot 4 | Students in Examination Rooms |
| Shot 5 | Father and Son Ages |
Run Inference
./build/bin/llama-cli \
-m /path/to/models/Thinklite-27B-NVFP4.gguf \
--spec-type draft-mtp \
--spec-draft-n-max 2 \
-ngl 99 \
-c 16384 \
--cache-type-k q8_0 \
--seed 42 \
-n 8192 \
-st \
-p "Your prompt here"
Performance results reflect this specific hardware and inference configuration. Actual throughput may vary depending on the prompt, model, software build, and runtime settings.
Snapshots (5)
llama.cpp
LLM inference in C/C++ β https://github.com/ggml-org/llama.cpp
Quantized using llama.cpp by prithivMLmods.
- Downloads last month
- 339
4-bit





