Instructions to use KikoCis/ALIA-40b-instruct-2601-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KikoCis/ALIA-40b-instruct-2601-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="KikoCis/ALIA-40b-instruct-2601-GGUF",
	filename="ALIA-40b-instruct-2601-IQ2_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use KikoCis/ALIA-40b-instruct-2601-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 KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M

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 KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M

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 KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M

Use Docker

docker model run hf.co/KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use KikoCis/ALIA-40b-instruct-2601-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KikoCis/ALIA-40b-instruct-2601-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": "KikoCis/ALIA-40b-instruct-2601-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M

Ollama
How to use KikoCis/ALIA-40b-instruct-2601-GGUF with Ollama:
```
ollama run hf.co/KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M
```

Unsloth Studio

How to use KikoCis/ALIA-40b-instruct-2601-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 KikoCis/ALIA-40b-instruct-2601-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 KikoCis/ALIA-40b-instruct-2601-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for KikoCis/ALIA-40b-instruct-2601-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use KikoCis/ALIA-40b-instruct-2601-GGUF with Docker Model Runner:
```
docker model run hf.co/KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M
```

Lemonade

How to use KikoCis/ALIA-40b-instruct-2601-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ALIA-40b-instruct-2601-GGUF-Q4_K_M

List all available models

lemonade list

KIKOCIS // EU-SOVEREIGN LLM // IMATRIX GGUF + KLD
   ╔═══════════════════╗
   ║   A L I A · 40B   ║  ES·CA·GL·EU
   ╚═══════════════════╝
   ┌───┐ ┌───┐ ┌───┐ ┌───┐
   │IQ2│ │Q3 │ │Q4 │ │Q8 │
   └───┘ └───┘ └───┘ └───┘
    ●─────●─────●─────●
       KLD vs Q8-ref
ALIA-40b · GGUF
llama · 46B · 160K ctx · imatrix (es) · KLD-measured

    
      FORMAT
GGUF (imatrix)

      SIZES
~13.5 – 40 GB

      ARCH
Llama · 46B · 48L

      CONTEXT
163840

    

      IMATRIX
es corpus

      VALIDATION
KLD vs Q8

      LANGUAGES
ES·CA·GL·EU·EN

      LICENSE
Apache-2.0

    

ALIA-40b-instruct-2601 — GGUF (imatrix + KLD)

imatrix-quantized GGUFs of ALIA-40b, the Barcelona Supercomputing Center's ~46B sovereign LLM for Spain / the EU (Spanish + Catalan, Galician, Basque + European languages), with a 160K native context. Runs from ~13.5 GB (IQ2_M) to ~40 GB (Q8_0). Calibrated (imatrix) on Spanish text, with per-quant KLD fidelity vs the near-lossless Q8_0 reference. Credit: this is BSC-LT's model — BSC-LT/ALIA-40b-instruct-2601; ours is the quant ladder + metrics.

✅ Recommended files

Use case	File	Notes
Safe default	`ALIA-40b-instruct-2601-Q4_K_M.gguf`	The one most people want — good quality, ~23 GB (48 GB RAM).
Strong quality/size	`ALIA-40b-instruct-2601-Q5_K_M.gguf`	Closer to the reference, ~27 GB.
Runs on 32 GB	`ALIA-40b-instruct-2601-Q3_K_M.gguf`	~19 GB — fits a 32 GB machine.
Smallest (tight RAM)	`ALIA-40b-instruct-2601-IQ2_M.gguf`	~13.5 GB i-quant — runs a 46B on 24–32 GB, at a real quality cost.
Reference / max fidelity	`ALIA-40b-instruct-2601-Q8_0.gguf`	~40 GB, near-lossless (the KLD reference).

📦 Files (the ladder)

Quant	Bits	File size	RAM (approx)	Notes
IQ2_M	~2.7	~13.5 GB	24–32 GB	Smallest — aggressive i-quant.
Q3_K_M	3	~18.7 GB	32 GB	Fits a 32 GB machine.
Q4_K_M	4	~22.9 GB	48 GB	Safe default.
Q5_K_M	5	~26.8 GB	48–64 GB	Strong quality/size.
Q8_0	8	~40 GB	64 GB+	Reference, near-lossless.

📊 Metrics — fidelity vs the Q8_0 reference

KLD (Kullback–Leibler divergence, nats) measures how far each quant's output distribution drifts from the reference — lower = closer. Top-1 match = how often the quant's top token agrees with the reference. Measured with llama-perplexity --kl-divergence over a Spanish corpus at ctx 512.

Why the reference is Q8_0, not F16? ALIA-40b's F16 is ~81 GB and does not fit this machine's GPU (Metal). Q8_0 is near-lossless (its own KLD vs F16 would be ~0.005), so it's a faithful stand-in reference for measuring how much the smaller quants drift. KLD values here are therefore relative to Q8_0 (Q8_0 = 0 by definition).

Model	Size GB	KLD mean	KLD p95	KLD max	Top-1 match
Q8_0 (reference)	40.0	0.0000	0.0000	0.0000	100.0%
Q5_K_M	26.78	0.0098	0.0408	4.893	96.61%
Q4_K_M	22.90	0.0337	0.1505	4.105	93.94%
Q3_K_M	18.67	0.1114	0.5419	7.904	88.89%
IQ2_M	13.54	0.3799	1.9178	12.259	77.82%

_{Full per-quant reports in reports/; machine-readable summary in metrics/quant-summary.csv; SHA-256 of every file in reports/artifact-sha256sums.txt.}

📈 Charts

🧮 Will it fit? (RAM cheat-sheet)

A 46B is memory-hungry; add KV-cache on top (it grows with context — 160K is a lot).

you have	quant	context
24 GB	IQ2_M	~8–16K
32 GB	Q3_K_M / IQ2_M	~16–32K
48 GB	Q4_K_M / Q5_K_M	~32–64K
64 GB+	Q8_0	large (up to 160K with room)

🚀 How to run it

# ollama
ollama run hf.co/KikoCis/ALIA-40b-instruct-2601-GGUF:Q4_K_M

# llama.cpp
llama-server -m ALIA-40b-instruct-2601-Q4_K_M.gguf -c 32768 --jinja -ngl 99

Recommended sampling: temperature ~0.7, top_p ~0.9. Chat/instruct model (uses its built-in template) — great for Spanish and the co-official languages (Catalan, Galician, Basque) + European languages.

⚠️ Good to know

Strengths: a genuinely sovereign, EU-built 46B — strong Spanish + co-official + European multilinguality, 160K context, permissive licence.
Limits: it's a 46B — even the smallest quant needs ~24 GB RAM; IQ2_M trades real quality for size. Not a specialised coding model.
KLD is measured vs Q8_0 (F16 doesn't fit this GPU) — see the note above.

📊 Evaluation methodology

What: quantization fidelity vs the Q8_0 reference — llama-perplexity --kl-divergence (KLD mean/p95/max, ΔPPL, top-1 agreement).
Corpus: Spanish text, ctx 512, same corpus used for imatrix calibration.
Reference: Q8_0 (near-lossless stand-in for F16, which is too large for this GPU).
Date: 2026-07. Caveat: relative fidelity ranking across quants of this model.

🔁 Provenance & reproducibility

Scripts: scripts/ — exact convert → Q8 → imatrix → quant → KLD commands.
imatrix: alia-40b-es.imatrix — importance matrix (Spanish calibration).
Checksums: reports/artifact-sha256sums.txt.
Source: BSC-LT/ALIA-40b-instruct-2601 — weights unmodified (faithful quantization).

🗒️ Changelog

2026-07 v1: initial imatrix GGUF ladder (IQ2_M → Q8_0) + KLD metrics, Spanish-calibrated.

📚 Credit & license

Model, weights, training: © Barcelona Supercomputing Center — the ALIA / langtech-bsc project (model · ALIA-kit). Quant ladder + imatrix (es) + KLD metrics: KikoCis. Apache-2.0 (same as upstream). No weights modified.

Downloads last month: 348

GGUF

Model size

40B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

8-bit

Model tree for KikoCis/ALIA-40b-instruct-2601-GGUF

Base model

BSC-LT/ALIA-40b

Finetuned

BSC-LT/ALIA-40b-instruct-2601

Quantized

(11)

this model

FORMAT GGUF (imatrix)	SIZES ~13.5 – 40 GB	ARCH Llama · 46B · 48L	CONTEXT 163840
IMATRIX es corpus	VALIDATION KLD vs Q8	LANGUAGES ES·CA·GL·EU·EN	LICENSE Apache-2.0