Instructions to use montevive/ALIA-40b-fc-2605-NVFP4-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 montevive/ALIA-40b-fc-2605-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 montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4

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 montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4

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 montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4

Use Docker

docker model run hf.co/montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4

LM Studio
Jan

vLLM

How to use montevive/ALIA-40b-fc-2605-NVFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "montevive/ALIA-40b-fc-2605-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": "montevive/ALIA-40b-fc-2605-NVFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4

Ollama
How to use montevive/ALIA-40b-fc-2605-NVFP4-GGUF with Ollama:
```
ollama run hf.co/montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4
```

Unsloth Studio

How to use montevive/ALIA-40b-fc-2605-NVFP4-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 montevive/ALIA-40b-fc-2605-NVFP4-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 montevive/ALIA-40b-fc-2605-NVFP4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for montevive/ALIA-40b-fc-2605-NVFP4-GGUF to start chatting

How to use montevive/ALIA-40b-fc-2605-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 montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4

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": "montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use montevive/ALIA-40b-fc-2605-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 montevive/ALIA-40b-fc-2605-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://127.0.0.1:8080/v1 \
  --custom-model-id "montevive/ALIA-40b-fc-2605-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"

Docker Model Runner
How to use montevive/ALIA-40b-fc-2605-NVFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4
```

Lemonade

How to use montevive/ALIA-40b-fc-2605-NVFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4

Run and chat with the model

lemonade run user.ALIA-40b-fc-2605-NVFP4-GGUF-NVFP4

List all available models

lemonade list

Hermes Agent

How to use montevive/ALIA-40b-fc-2605-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 montevive/ALIA-40b-fc-2605-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://127.0.0.1:8080/v1
hermes config set model.default montevive/ALIA-40b-fc-2605-NVFP4-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat

ALIA-40b-fc-2605 — NVFP4 GGUF

NVFP4 quantization of BSC-LT/ALIA-40b-fc-2605 packaged for llama.cpp. 27 GB on disk, ~10 tok/s generation on a single NVIDIA GB10 (DGX Spark). This is the function-calling fine-tune of the ALIA-40b base — it emits OpenAI-style <tool_call> JSON blocks when given a tools list at prompt time.

For the vLLM / TensorRT-LLM (compressed-tensors safetensors) version, see montevive/ALIA-40b-fc-2605-NVFP4.

File	Format	Size	Use case
`ALIA-40b-fc-2605.NVFP4.gguf`	NVFP4 (`GGML_TYPE_NVFP4`, type 40)	26.8 GiB	Blackwell GPUs (RTX 50xx, GB10, B-series), llama.cpp

Tool calling

The function-calling capability is the differentiator vs ALIA-40b-instruct-2601. Pass an OpenAI-style tools array in the chat template and the model emits one or more <tool_call>{...}</tool_call> blocks, parseable as JSON with name and arguments keys.

from transformers import AutoTokenizer
tok = AutoTokenizer.from_pretrained("BSC-LT/ALIA-40b-fc-2605")

tools = [{
    "type": "function",
    "name": "get_weather",
    "description": "Get current temperature for a given location.",
    "parameters": {
        "type": "object",
        "properties": {"location": {"type": "string", "description": "City and country e.g. 'Madrid, Spain'"}},
        "required": ["location"],
        "additionalProperties": False,
    },
}]

prompt = tok.apply_chat_template(
    [{"role": "user", "content": "What's the weather in Paris?"}],
    tokenize=False, add_generation_prompt=True, tools=tools,
)
# → ...<tool_call>{"name": "get_weather", "arguments": {"location": "Paris, France"}}</tool_call>

In llama.cpp, the --jinja flag picks up the model's embedded chat template (including tools rendering) automatically. The llama-server OpenAI-compatible endpoint exposes tool calling via the standard tools request parameter; clients should parse the <tool_call> blocks from the response or rely on llama.cpp's hermes tool-call parser.

Usage

Requires a recent llama.cpp build. NVFP4 was added in PR #19769 (March 2026); the Llama-architecture Q/K RoPE permute fix needed for correct NVFP4 GGUF output was merged in PR #22611 (May 2026). On Blackwell hardware (compute capability ≥ 12.0), PR #22196 provides native tensor-core acceleration.

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build -DGGML_CUDA=ON -DCMAKE_BUILD_TYPE=Release
cmake --build build -j$(nproc)

# Chat with tool calling enabled — --jinja honors the embedded template.
./build/bin/llama-cli \
    -m ALIA-40b-fc-2605.NVFP4.gguf \
    -ngl 99 -c 4096 \
    --jinja -cnv

# Or as an OpenAI-compatible server with WebUI on http://localhost:8080
./build/bin/llama-server \
    -m ALIA-40b-fc-2605.NVFP4.gguf \
    -ngl 99 -c 4096 --jinja --host 0.0.0.0 --port 8080

Recommended sampling (per the base model card): temperature between 0 and 0.2; avoid repetition penalties — they degrade instruction-following and tool-call validity.

Performance

Architecturally identical to ALIA-40b-instruct-2601 (LlamaForCausalLM, 48 layers, hidden 8192, 64/8 heads, vocab 256k). Expect equivalent throughput on Blackwell — ~10 tok/s generation on a single NVIDIA GB10 (DGX Spark) at -ngl 99 -c 4096 --jinja.

Backend	Format	Token gen (single prompt, GB10)
GPU (`-ngl 99`)	NVFP4	~10 tok/s
GPU (`-ngl 99`)	Q8_0	~5 tok/s

On non-Blackwell hardware, Q4_K_M / Q5_K_M / Q8_0 from the BF16 source remain better trade-offs because their kernels are more mature.

Quantization details

Source: BSC-LT/ALIA-40b-fc-2605 BF16 (~76 GB across 17 shards)
Tool: NVIDIA ModelOpt NVFP4 → convert_hf_to_gguf.py (llama.cpp master, post-PR #22611)
Scheme: NVFP4 (NVFP4_DEFAULT_CFG)
Calibration: 128 samples of HuggingFaceH4/ultrachat_200k (train_sft split), max_seq_len 2048
Ignored layers: lm_head

Calibration caveat

ultrachat_200k is English-only synthetic chat. The originally planned mix with Salesforce/xlam-function-calling-60k (function-calling traces) was blocked at run time because that dataset is gated on HF, so calibration fell back to the proven 2601 recipe. The model's FC distribution is already encoded in its SFT weights, but per-tensor scales were computed against a chat-only activation distribution, which may underweight tool-call activation patterns. BSC themselves note the FC fine-tune is "primarily evaluated and optimized for English," so English chat and tool calling should be well-served; multilingual tool calling (Spanish/Catalan/Basque/Galician) may be more affected by quantization noise than prose. Evaluate on your own multilingual tool-call task before deploying.

License & attribution

Released under the same Apache 2.0 license as the source.

Base model: BSC-LT/ALIA-40b-fc-2605 by Barcelona Supercomputing Center (BSC). Please cite their work if you use this model in research:

@misc{alia-40b-fc-2605,
  author = {Barcelona Supercomputing Center},
  title  = {ALIA-40b-fc-2605},
  year   = {2026},
  url    = {https://huggingface.co/BSC-LT/ALIA-40b-fc-2605}
}

NVFP4 quantization: Montevive AI.

Limitations

Inherits all limitations of the base ALIA-40b-fc-2605 model, including:

Not safety-aligned. BSC's model card explicitly notes the FC fine-tune is instruction-tuned but lacks value alignment. Apply your own guardrails before production use.
Tool calling is English-optimized. BSC's BFCL numbers (Non-Live Multiple AST 94.5%, Live Multiple AST 74.4%) are English; multilingual tool calling is on BSC's roadmap but not yet evaluated.
Multi-turn tool calling is weaker than single-turn (BFCL Multi-Turn Base 15.5% on BF16, per BSC's card). Don't expect long agentic loops without external scaffolding.

Plus standard NVFP4 quantization caveats:

NVFP4 inference quality is below Q8_0 on small models. ALIA-40b is well within NVFP4's design sweet spot (originally targeted at 70B+) but evaluate on your task before deploying.
CPU performance is poor — ARM NEON dot product for NVFP4 is much newer than for Q8_0 / K-quants. Use Blackwell GPUs for real workloads.

Downloads last month: 122

GGUF

Model size

40B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for montevive/ALIA-40b-fc-2605-NVFP4-GGUF

Base model

BSC-LT/ALIA-40b

Finetuned

BSC-LT/ALIA-40b-fc-2605

Quantized

(5)

this model