You can deploy this model and start earning money today!

Slmkrnz/
promptmon-llama-3.2-3b-GGUF

Name: promptmon-llama-3.2-3b-GGUF
Availability: InStock

meta-llama/Llama-3.2-3B-Instruct

Views

No views yet

PromptMon Llama 3.2 3B — GGUF (Q4_K_M)

Llama 3.2 3B Instruct fused with the PromptMon LoRA v2 adapter, converted to GGUF and quantized to Q4_K_M for on-device mobile inference (fllama / llama.cpp).

Base: meta-llama/Llama-3.2-3B-Instruct
Adapter: LoRA rank 8, trained on 170 PromptMon duel turns (val loss 0.576)
Quantization: Q4_K_M (~1.92 GB, 5.01 BPW)
Target runtime: fllama on iOS/Android, llama.cpp on desktop

Use the Llama 3.2 chat template — PromptMon prompts assume it verbatim.

License

Inherits Llama 3.2 Community License.

Slmkrnz/promptmon-llama-3.2-3b-GGUF

PromptMon Llama 3.2 3B — GGUF (Q4_K_M)

License

Slmkrnz/
promptmon-llama-3.2-3b-GGUF