microsoft/Phi-3-medium-128k-instruct
LlamaEdge version: v0.11.2 and above
Prompt template
Prompt type: phi-3-chat
Prompt string
<|system|>
{system_message}<|end|>
<|user|>
{user_message_1}<|end|>
<|assistant|>
{assistant_message_1}<|end|>
<|user|>
{user_message_2}<|end|>
<|assistant|>
Context size: 128000
Run as LlamaEdge service
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-3-medium-128k-instruct-Q5_K_M.gguf \
llama-api-server.wasm \
--prompt-template phi-3-chat \
--ctx-size 128000 \
--model-name phi-3-medium-128k
Run as LlamaEdge command app
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-3-medium-128k-instruct-Q5_K_M.gguf \
llama-chat.wasm \
--prompt-template phi-3-chat \
--ctx-size 128000
| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| Phi-3-medium-128k-instruct-Q2_K.gguf | Q2_K | 2 | 5.14 GB | smallest, significant quality loss - not recommended for most purposes |
| Phi-3-medium-128k-instruct-Q3_K_L.gguf | Q3_K_L | 3 | 7.49 GB | small, substantial quality loss |
| Phi-3-medium-128k-instruct-Q3_K_M.gguf | Q3_K_M | 3 | 6.92 GB | very small, high quality loss |
| Phi-3-medium-128k-instruct-Q3_K_S.gguf | Q3_K_S | 3 | 6.06 GB | very small, high quality loss |
| Phi-3-medium-128k-instruct-Q4_0.gguf | Q4_0 | 4 | 7.9 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Phi-3-medium-128k-instruct-Q4_K_M.gguf | Q4_K_M | 4 | 8.57 GB | medium, balanced quality - recommended |
| Phi-3-medium-128k-instruct-Q4_K_S.gguf | Q4_K_S | 4 | 7.95 GB | small, greater quality loss |
| Phi-3-medium-128k-instruct-Q5_0.gguf | Q5_0 | 5 | 9.62 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Phi-3-medium-128k-instruct-Q5_K_M.gguf | Q5_K_M | 5 | 10.1 GB | large, very low quality loss - recommended |
| Phi-3-medium-128k-instruct-Q5_K_S.gguf | Q5_K_S | 5 | 9.62 GB | large, low quality loss - recommended |
| Phi-3-medium-128k-instruct-Q6_K.gguf | Q6_K | 6 | 11.5 GB | very large, extremely low quality loss |
| Phi-3-medium-128k-instruct-Q8_0.gguf | Q8_0 | 8 | 14.8 GB | very large, extremely low quality loss - not recommended |
| Phi-3-medium-128k-instruct-f16.gguf | f16 | 16 | 27.9 GB |
Quantized with llama.cpp b2961.
Have the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo second-state/Phi-3-medium-128k-instruct-GGUF ./model-foldermicrosoft/Phi-3-medium-128k-instruct