You can deploy this model and start earning money today!

RichardErkhov/
NAMJOON_-_smu_counsel_vllm16_llama3.2_v1-gguf

Name: NAMJOON_-_smu_counsel_vllm16_llama3.2_v1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

smu_counsel_vllm16_llama3.2_v1 - GGUF

Name	Quant method	Size
smu_counsel_vllm16_llama3.2_v1.Q2_K.gguf	Q2_K	1.27GB
smu_counsel_vllm16_llama3.2_v1.IQ3_XS.gguf	IQ3_XS	1.38GB
smu_counsel_vllm16_llama3.2_v1.IQ3_S.gguf	IQ3_S	1.44GB
smu_counsel_vllm16_llama3.2_v1.Q3_K_S.gguf	Q3_K_S	1.44GB
smu_counsel_vllm16_llama3.2_v1.IQ3_M.gguf	IQ3_M	1.49GB
smu_counsel_vllm16_llama3.2_v1.Q3_K.gguf	Q3_K	1.57GB
smu_counsel_vllm16_llama3.2_v1.Q3_K_M.gguf	Q3_K_M	1.57GB
smu_counsel_vllm16_llama3.2_v1.Q3_K_L.gguf	Q3_K_L	1.69GB
smu_counsel_vllm16_llama3.2_v1.IQ4_XS.gguf	IQ4_XS	1.71GB
smu_counsel_vllm16_llama3.2_v1.Q4_0.gguf	Q4_0	1.79GB
smu_counsel_vllm16_llama3.2_v1.IQ4_NL.gguf	IQ4_NL	1.79GB
smu_counsel_vllm16_llama3.2_v1.Q4_K_S.gguf	Q4_K_S	1.8GB
smu_counsel_vllm16_llama3.2_v1.Q4_K.gguf	Q4_K	1.88GB
smu_counsel_vllm16_llama3.2_v1.Q4_K_M.gguf	Q4_K_M	1.88GB
smu_counsel_vllm16_llama3.2_v1.Q4_1.gguf	Q4_1	1.95GB
smu_counsel_vllm16_llama3.2_v1.Q5_0.gguf	Q5_0	2.11GB
smu_counsel_vllm16_llama3.2_v1.Q5_K_S.gguf	Q5_K_S	2.11GB
smu_counsel_vllm16_llama3.2_v1.Q5_K.gguf	Q5_K	2.16GB
smu_counsel_vllm16_llama3.2_v1.Q5_K_M.gguf	Q5_K_M	2.16GB
smu_counsel_vllm16_llama3.2_v1.Q5_1.gguf	Q5_1	2.28GB
smu_counsel_vllm16_llama3.2_v1.Q6_K.gguf	Q6_K	2.46GB
smu_counsel_vllm16_llama3.2_v1.Q8_0.gguf	Q8_0	3.19GB

Original model description:

base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit language:

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.