Instructions to use Hob-forge/BAR-5x7B-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 Hob-forge/BAR-5x7B-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 Hob-forge/BAR-5x7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hob-forge/BAR-5x7B-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 Hob-forge/BAR-5x7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hob-forge/BAR-5x7B-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 Hob-forge/BAR-5x7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Hob-forge/BAR-5x7B-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 Hob-forge/BAR-5x7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Hob-forge/BAR-5x7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Hob-forge/BAR-5x7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Hob-forge/BAR-5x7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hob-forge/BAR-5x7B-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": "Hob-forge/BAR-5x7B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hob-forge/BAR-5x7B-GGUF:Q4_K_M

Ollama
How to use Hob-forge/BAR-5x7B-GGUF with Ollama:
```
ollama run hf.co/Hob-forge/BAR-5x7B-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Hob-forge/BAR-5x7B-GGUF with Docker Model Runner:
```
docker model run hf.co/Hob-forge/BAR-5x7B-GGUF:Q4_K_M
```

Lemonade

How to use Hob-forge/BAR-5x7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Hob-forge/BAR-5x7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.BAR-5x7B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

BAR-5x7B-GGUF / README.md

RhinoWithAcape

metadata: enrich discovery tags (quants, hardware fit, runtimes)

b8bd377 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.44 kB

metadata

license: apache-2.0
base_model: allenai/BAR-5x7B
tags:
  - allenai
  - bar
  - flex-olmo
  - olmo
  - moe
  - mixture-of-experts
  - gguf
  - llama.cpp
  - quantized
  - q4_k_m
  - 16gb
  - 24gb
language:
  - en
pipeline_tag: text-generation
library_name: gguf
base_model_relation: quantized

BAR-5x7B — GGUF (first-of-its-kind FlexOlmo conversion)

This is the first GGUF conversion of allenai/BAR-5x7B, the largest member of AllenAI's BAR-family Mixture-of-Experts models released on 2026-04-19 based on the new FlexOlmo architecture.

5 experts × 7B → ~33B total parameters with top-k routing.

⚠ Requires patched llama.cpp

The FlexOlmo architecture is not yet supported in upstream llama.cpp. To run this GGUF use the FlexOlmo support fork:

Fork: https://github.com/Seraphiel102/llama.cpp/tree/flex-olmo-pr-clean

Build from the fork:

git clone https://github.com/Seraphiel102/llama.cpp.git
cd llama.cpp
git checkout flex-olmo-pr-clean
cmake -B build -DGGML_CUDA=OFF
cmake --build build -j --target llama-cli llama-quantize llama-completion

What FlexOlmo is

Per transformers.models.flex_olmo, FlexOlmoDecoderLayer is Olmo2's hybrid post-norm decoder layer with the dense FFN swapped for OlmoE-style top-k MoE routing. Specifically:

Attention with q_norm and k_norm (Olmo2-style)
post_attention_layernorm and post_feedforward_layernorm (post-norm pattern, no input_layernorm)
Top-k MoE FFN with softmax routing (OlmoE-style)
No sliding-window attention

Files

Quant	Size	Notes
`BAR-5x7B.Q4_K_M.gguf`	14 GB	recommended, fits 16GB VRAM at small context
(more quants pending)

Usage

./build/bin/llama-completion \
  -m BAR-5x7B.Q4_K_M.gguf \
  -p "The 5 experts in BAR-5x7B are " \
  -n 100

Validation

The Q4_K_M conversion was validated against the patched llama.cpp build using a basic arithmetic prompt and produces correct, coherent output.

Credit

Model: AllenAI — allenai/BAR-5x7B
FlexOlmo support in llama.cpp: PR by @Seraphiel102 / Nyx
Conversion: llama.cpp + the convert_hf_to_gguf.py patch from the support PR

If this saved you time, please ⭐ the llama.cpp PR.