Aleksey Nikiforov's picture

25 3

Aleksey Nikiforov

anikifoss

·

AI & ML interests

DeepSeek R1

Recent Activity

new activity about 11 hours ago

ubergarm/DeepSeek-V3.1-GGUF:quant req: 256 GB RAM + 96 GB VRAM

new activity 5 days ago

cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit:Thank You!

liked a model 5 days ago

cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit

View all activity

Organizations

None yet

New activity in ubergarm/DeepSeek-V3.1-GGUF about 11 hours ago

quant req: 256 GB RAM + 96 GB VRAM

#1 opened 2 days ago by

New activity in cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit 5 days ago

Thank You!

#1 opened 5 days ago by

New activity in ubergarm/GLM-4.5-Air-GGUF 6 days ago

Can you provide some low-precision quantization options?

#3 opened 19 days ago by

New activity in anikifoss/GLM-4.5-Air-HQ4_K 14 days ago

Performance? Methodology?

#2 opened 14 days ago by

New activity in anikifoss/Kimi-K2-Instruct-DQ4_K 16 days ago

Thank you

#1 opened about 1 month ago by

Updaed Chat-Template

#4 opened 16 days ago by

New activity in anikifoss/Qwen3-Coder-480B-A35B-Instruct-HQ4_K 16 days ago

Re-Uploaded Fixed Version

#1 opened 16 days ago by

New activity in anikifoss/Qwen3-235B-A22B-Thinking-2507-HQ4_K 17 days ago

Quantization Script Issue - Reuploading

#1 opened 19 days ago by

New activity in anikifoss/Qwen3-235B-A22B-Instruct-2507-HQ4_K 17 days ago

Re-Uploaded Fixed Version

#1 opened 17 days ago by

New activity in anikifoss/GLM-4.5-HQ4_K 17 days ago

Re-Uploaded with BF16 Tensors

#1 opened 17 days ago by

New activity in anikifoss/GLM-4.5-Air-HQ4_K 17 days ago

Re-Uploaded with BF16 Tensors

#1 opened 17 days ago by

New activity in btbtyler09/Qwen3-30B-A3B-gptq-8bit 23 days ago

4-bit

#1 opened 4 months ago by

prashanthellina

New activity in ubergarm/Qwen3-30B-A3B-Instruct-2507-GGUF 25 days ago

Add comparison with Q_K quants

#1 opened 25 days ago by

New activity in ubergarm/Qwen3-235B-A22B-Thinking-2507-GGUF 29 days ago

Thank you!

#1 opened 29 days ago by

New activity in anikifoss/Kimi-K2-Instruct-DQ4_K about 1 month ago

Great quality model! Very low perplexity!

#3 opened about 1 month ago by

What sort of performance numbers are you seeing with llama.cpp and ik_llama?

#2 opened about 1 month ago by

New activity in unsloth/Kimi-K2-Instruct-GGUF about 1 month ago

The correct eos_token_id value for Kimi-K2-Instruct

#11 opened about 1 month ago by

New activity in ubergarm/Kimi-K2-Instruct-GGUF about 1 month ago

Can't wait!

#1 opened about 1 month ago by

New activity in gabriellarson/Kimi-K2-Instruct-GGUF about 1 month ago

Thanks for the mainline llama.cpp PR effort!

#1 opened about 1 month ago by

New activity in ubergarm/Hunyuan-A13B-Instruct-GGUF about 1 month ago

Hunyuan-A13B Coding Performance

#5 opened about 2 months ago by