You can deploy this model and start earning money today!

RichardErkhov/
mahiatlinux_-_QuestingQwen-Instruct-v1-test2-gguf

Name: mahiatlinux_-_QuestingQwen-Instruct-v1-test2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

QuestingQwen-Instruct-v1-test2 - GGUF

Name	Quant method	Size
QuestingQwen-Instruct-v1-test2.Q2_K.gguf	Q2_K	1.51GB
QuestingQwen-Instruct-v1-test2.IQ3_XS.gguf	IQ3_XS	1.66GB
QuestingQwen-Instruct-v1-test2.IQ3_S.gguf	IQ3_S	1.73GB
QuestingQwen-Instruct-v1-test2.Q3_K_S.gguf	Q3_K_S	1.73GB
QuestingQwen-Instruct-v1-test2.IQ3_M.gguf	IQ3_M	1.81GB
QuestingQwen-Instruct-v1-test2.Q3_K.gguf	Q3_K	1.89GB
QuestingQwen-Instruct-v1-test2.Q3_K_M.gguf	Q3_K_M	1.89GB
QuestingQwen-Instruct-v1-test2.Q3_K_L.gguf	Q3_K_L	2.03GB
QuestingQwen-Instruct-v1-test2.IQ4_XS.gguf	IQ4_XS	2.08GB
QuestingQwen-Instruct-v1-test2.Q4_0.gguf	Q4_0	2.17GB
QuestingQwen-Instruct-v1-test2.IQ4_NL.gguf	IQ4_NL	2.18GB
QuestingQwen-Instruct-v1-test2.Q4_K_S.gguf	Q4_K_S	2.18GB
QuestingQwen-Instruct-v1-test2.Q4_K.gguf	Q4_K	2.29GB
QuestingQwen-Instruct-v1-test2.Q4_K_M.gguf	Q4_K_M	2.29GB
QuestingQwen-Instruct-v1-test2.Q4_1.gguf	Q4_1	2.38GB
QuestingQwen-Instruct-v1-test2.Q5_0.gguf	Q5_0	2.58GB
QuestingQwen-Instruct-v1-test2.Q5_K_S.gguf	Q5_K_S	2.58GB
QuestingQwen-Instruct-v1-test2.Q5_K.gguf	Q5_K	2.64GB
QuestingQwen-Instruct-v1-test2.Q5_K_M.gguf	Q5_K_M	2.64GB
QuestingQwen-Instruct-v1-test2.Q5_1.gguf	Q5_1	2.79GB
QuestingQwen-Instruct-v1-test2.Q6_K.gguf	Q6_K	3.03GB
QuestingQwen-Instruct-v1-test2.Q8_0.gguf	Q8_0	3.92GB

Original model description:

base_model: Qwen/Qwen1.5-4B language:

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.