Falcon3-10B-Instruct-GGUF/README.md

base_model, license, license_name, license_link, model_creator, model_name, quantized_by, language, library_name, tags

base_model	license	license_name	license_link	model_creator	model_name	quantized_by	language	library_name	tags
tiiuae/Falcon3-10B-Instruct	other	falcon-llm-license	https://falconllm.tii.ae/falcon-terms-and-conditions.html	tiiuae	Falcon3-10B-Instruct	Second State Inc.	en fr es pt	transformers	falcon3

---

Falcon3-10B-Instruct-GGUF

Original Model

tiiuae/Falcon3-10B-Instruct

Run with LlamaEdge

• LlamaEdge version: v0.16.0 and above

• Prompt template

  • Prompt type: falcon3

  • Prompt string

    <|system|>
    You are a helpful friendly assistant Falcon3 from TII, try to follow instructions as much as possible.
    <|user|>
    {user_message}
    <|assistant|>
    

• Context size: 32000

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Falcon3-10B-Instruct-Q5_K_M.gguf \
    llama-api-server.wasm \
    --model-name Falcon3-10B-Instruct \
    --prompt-template falcon3 \
    --ctx-size 32000
  

• Run as LlamaEdge command app

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Falcon3-10B-Instruct-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template falcon3 \
    --ctx-size 32000
  

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Falcon3-10B-Instruct-Q2_K.gguf	Q2_K	2	3.92 GB	smallest, significant quality loss - not recommended for most purposes
Falcon3-10B-Instruct-Q3_K_L.gguf	Q3_K_L	3	5.45 GB	small, substantial quality loss
Falcon3-10B-Instruct-Q3_K_M.gguf	Q3_K_M	3	5.05 GB	very small, high quality loss
Falcon3-10B-Instruct-Q3_K_S.gguf	Q3_K_S	3	4.59 GB	very small, high quality loss
Falcon3-10B-Instruct-Q4_0.gguf	Q4_0	4	5.91 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Falcon3-10B-Instruct-Q4_K_M.gguf	Q4_K_M	4	6.29 GB	medium, balanced quality - recommended
Falcon3-10B-Instruct-Q4_K_S.gguf	Q4_K_S	4	5.95 GB	small, greater quality loss
Falcon3-10B-Instruct-Q5_0.gguf	Q5_0	5	7.14 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Falcon3-10B-Instruct-Q5_K_M.gguf	Q5_K_M	5	7.34 GB	large, very low quality loss - recommended
Falcon3-10B-Instruct-Q5_K_S.gguf	Q5_K_S	5	7.14 GB	large, low quality loss - recommended
Falcon3-10B-Instruct-Q6_K.gguf	Q6_K	6	8.46 GB	very large, extremely low quality loss
Falcon3-10B-Instruct-Q8_0.gguf	Q8_0	8	11.0 GB	very large, extremely low quality loss - not recommended
Falcon3-10B-Instruct-f16.gguf	f16	16	20.6 GB

Quantized with llama.cpp b4381