Alexone's picture

33

Alexone

krustik

·

AI & ML interests

Testing Evaluating

Recent Activity

new activity 2 days ago

meta-llama/Llama-4-Scout-17B-16E-Instruct:Unethical comparisons with Deepseek replacing chinese languages by thai/vietnamese only

new activity 10 days ago

allenai/Llama-3.1-Tulu-3-405B:Test result

new activity 10 days ago

Qwen/Qwen2.5-Omni-7B:Where is the MLX version of qwen 2.5 Omni?

View all activity

Organizations

None yet

krustik's activity

New activity in meta-llama/Llama-4-Scout-17B-16E-Instruct 2 days ago

Unethical comparisons with Deepseek replacing chinese languages by thai/vietnamese only

#32 opened 2 days ago by

New activity in allenai/Llama-3.1-Tulu-3-405B 10 days ago

Test result

#2 opened about 2 months ago by

New activity in Qwen/Qwen2.5-Omni-7B 10 days ago

Where is the MLX version of qwen 2.5 Omni?

#22 opened 10 days ago by

New activity in bartowski/DeepSeek-R1-GGUF 10 days ago

Tested Q6, uses 567Gb Ram

#2 opened 2 months ago by

New activity in deepseek-ai/DeepSeek-V3-0324 10 days ago

Amazing, test result by 567Gb RAM on 10 years old hardware

#42 opened 11 days ago by

New activity in unsloth/DeepSeek-V3-0324-GGUF 11 days ago

How many bits of Quantization is enough for Code Generation Tasks?

#5 opened 11 days ago by

New activity in deepseek-ai/DeepSeek-V3-0324 11 days ago

Can a quantized version of deepseek-v3-0324 be implemented on a machine with a cluster of 8 *A100s?

#19 opened 14 days ago by

New activity in deepseek-ai/DeepSeek-V3-0324 12 days ago

Please, hurry up and release the quantized version!

#23 opened 14 days ago by

New activity in Qwen/QwQ-32B-GGUF about 1 month ago

Why many small files?

#1 opened about 1 month ago by

rdtfddgrffdgfdghfghdfujgdhgsf

New activity in yandex/YandexGPT-5-Lite-8B-pretrain about 1 month ago

Где gguf?

#2 opened about 1 month ago by

Огромное вам спасибо. Продолжение?

#5 opened about 1 month ago by

New activity in bartowski/Llama-3.1-Tulu-3-405B-GGUF about 2 months ago

Test result

#1 opened about 2 months ago by

New activity in unsloth/DeepSeek-R1-GGUF about 2 months ago

New research paper, R1 type reasoning models can be drastically improved in quality

#19 opened 2 months ago by

New activity in unsloth/DeepSeek-R1-GGUF 2 months ago

A Step-by-step deployment guide with ollama

#16 opened 2 months ago by

New activity in unsloth/DeepSeek-V3-GGUF 2 months ago

First review, Q5-K-M require 502Gb RAM, better than Meta 405billions

#11 opened 3 months ago by

New activity in deepseek-ai/DeepSeek-V3-Base 2 months ago

Resource Requirements for Running DeepSeek v3 Locally

#56 opened 3 months ago by

New activity in deepseek-ai/DeepSeek-V3 3 months ago

Smaller version for Home User GPU's

#2 opened 3 months ago by

New activity in unsloth/DeepSeek-R1-GGUF 3 months ago

What is the VRAM requirement to run this ?

#1 opened 3 months ago by

New activity in deepseek-ai/DeepSeek-V3 3 months ago

minimum vram?

#9 opened 3 months ago by

New activity in deepseek-ai/DeepSeek-V3-Base 3 months ago

You will release a small version for consumer hardware like the v2 generation?

#35 opened 3 months ago by

anon-linux-mint