Edit model card

image/png This model was quantized by SanctumAI. To leave feedback, join our community in Discord.

Phi 3 Mini 4K Instruct GGUF

Model creator: microsoft
Original model: Phi-3.5-mini-instruct

Model Summary:

Phi-3.5-mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.

Prompt Template:

If you're using Sanctum app, simply use Phi 3 model preset.

Prompt template:

<|system|>
{system_prompt}<|end|>
<|user|>
{prompt}<|end|>
<|assistant|>

Hardware Requirements Estimate

Name Quant method Size Memory (RAM, vRAM) required
phi-3.5-mini-instruct.Q2_K.gguf Q2_K 1.42 GB 5.02 GB
phi-3.5-mini-instruct.Q3_K_S.gguf Q3_K_S 1.68 GB 5.27 GB
phi-3.5-mini-instruct.Q3_K_M.gguf Q3_K_M 1.96 GB 5.52 GB
phi-3.5-mini-instruct.Q3_K_L.gguf Q3_K_L 2.09 GB 5.65 GB
phi-3.5-mini-instruct.Q4_0.gguf Q4_0 2.18 GB 5.73 GB
phi-3.5-mini-instruct.Q4_K_S.gguf Q4_K_S 2.19 GB 5.74 GB
phi-3.5-mini-instruct.Q4_K_M.gguf Q4_K_M 2.39 GB 5.93 GB
phi-3.5-mini-instruct.Q4_K.gguf Q4_K 2.39 GB 5.93 GB
phi-3.5-mini-instruct.Q4_1.gguf Q4_1 2.41 GB 5.94 GB
phi-3.5-mini-instruct.Q5_0.gguf Q5_0 2.64 GB 6.16 GB
phi-3.5-mini-instruct.Q5_K_S.gguf Q5_K_S 2.64 GB 6.16 GB
phi-3.5-mini-instruct.Q5_K_M.gguf Q5_K_M 2.82 GB 6.32 GB
phi-3.5-mini-instruct.Q5_K.gguf Q5_K 2.82 GB 6.32 GB
phi-3.5-mini-instruct.Q5_1.gguf Q5_1 2.87 GB 6.38 GB
phi-3.5-mini-instruct.Q6_K.gguf Q6_K 3.14 GB 6.62 GB
phi-3.5-mini-instruct.Q8_0.gguf Q8_0 4.06 GB 7.48 GB
phi-3.5-mini-instruct.f16.gguf f16 7.64 GB 10.82 GB

Disclaimer

Sanctum is not the creator, originator, or owner of any Model featured in the Models section of the Sanctum application. Each Model is created and provided by third parties. Sanctum does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Model listed there. You understand that supported Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Model is the sole responsibility of the person or entity who originated such Model. Sanctum may not monitor or control the Models supported and cannot, and does not, take responsibility for any such Model. Sanctum disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Models. Sanctum further disclaims any warranty that the Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Models, your downloading of any Model, or use of any other Model provided by or through Sanctum.

Downloads last month
7,057
GGUF
Model size
3.82B params
Architecture
phi3

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Examples
Inference API (serverless) is not available, repository is disabled.