You can deploy this model and start earning money today!

RichardErkhov/
TheBlueObserver_-_Falcon3-7B-Instruct-MLX-gguf

Name: TheBlueObserver_-_Falcon3-7B-Instruct-MLX-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Falcon3-7B-Instruct-MLX - GGUF

Model creator: https://huggingface.co/TheBlueObserver/
Original model: https://huggingface.co/TheBlueObserver/Falcon3-7B-Instruct-MLX/

Name	Quant method	Size
Falcon3-7B-Instruct-MLX.Q2_K.gguf	Q2_K	2.69GB
Falcon3-7B-Instruct-MLX.IQ3_XS.gguf	IQ3_XS	2.99GB
Falcon3-7B-Instruct-MLX.IQ3_S.gguf	IQ3_S	3.14GB
Falcon3-7B-Instruct-MLX.Q3_K_S.gguf	Q3_K_S	3.14GB
Falcon3-7B-Instruct-MLX.IQ3_M.gguf	IQ3_M	3.2GB
Falcon3-7B-Instruct-MLX.Q3_K.gguf	Q3_K	3.43GB
Falcon3-7B-Instruct-MLX.Q3_K_M.gguf	Q3_K_M	3.43GB
Falcon3-7B-Instruct-MLX.Q3_K_L.gguf	Q3_K_L	3.7GB
Falcon3-7B-Instruct-MLX.IQ4_XS.gguf	IQ4_XS	3.83GB
Falcon3-7B-Instruct-MLX.Q4_0.gguf	Q4_0	4.01GB
Falcon3-7B-Instruct-MLX.IQ4_NL.gguf	IQ4_NL	4.03GB
Falcon3-7B-Instruct-MLX.Q4_K_S.gguf	Q4_K_S	4.03GB
Falcon3-7B-Instruct-MLX.Q4_K.gguf	Q4_K	4.26GB
Falcon3-7B-Instruct-MLX.Q4_K_M.gguf	Q4_K_M	4.26GB
Falcon3-7B-Instruct-MLX.Q4_1.gguf	Q4_1	4.42GB
Falcon3-7B-Instruct-MLX.Q5_0.gguf	Q5_0	4.83GB
Falcon3-7B-Instruct-MLX.Q5_K_S.gguf	Q5_K_S	4.83GB
Falcon3-7B-Instruct-MLX.Q5_K.gguf	Q5_K	4.96GB
Falcon3-7B-Instruct-MLX.Q5_K_M.gguf	Q5_K_M	4.96GB
Falcon3-7B-Instruct-MLX.Q5_1.gguf	Q5_1	5.24GB
Falcon3-7B-Instruct-MLX.Q6_K.gguf	Q6_K	5.7GB
Falcon3-7B-Instruct-MLX.Q8_0.gguf	Q8_0	7.38GB

Original model description:

base_model: tiiuae/Falcon3-7B-Instruct language:

en
fr
es
pt library_name: transformers license: other license_name: falcon-llm-license license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html tags:
falcon3
mlx

TheBlueObserver/Falcon3-7B-Instruct-MLX

The Model TheBlueObserver/Falcon3-7B-Instruct-MLX was converted to MLX format from tiiuae/Falcon3-7B-Instruct using mlx-lm version 0.20.2.

Use with mlx

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("TheBlueObserver/Falcon3-7B-Instruct-MLX")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

RichardErkhov/TheBlueObserver_-_Falcon3-7B-Instruct-MLX-gguf

Original model description:

TheBlueObserver/Falcon3-7B-Instruct-MLX

Use with mlx

RichardErkhov/
TheBlueObserver_-_Falcon3-7B-Instruct-MLX-gguf