Roman Ivanov

perelmanych's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in vcruz305/DeepSeek-V4.1-Flash-GGUF 17 days ago

can llama.cpp run directly?

4

#1 opened 18 days ago by

pikaqiu888

New activity in unsloth/GLM-5.3-Flash-GGUF 23 days ago

All GLM-5.3-Flash quants are now available.

🔥 4

1

#10 opened 29 days ago by

danielhanchen

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF about 2 months ago

KLD Benchmarks + why Q8_K_XL vs MXFP4 naming

❤️👍 11

6

#11 opened about 2 months ago by

danielhanchen

Dual RTX3090 and 64GB DDR4 + 78GB Swap. Speed: ~1.78 TPS

🤝👍 4

15

#8 opened about 2 months ago by

robert1968

New activity in bartowski/Hy3-GGUF 2 months ago

Relative quant qualities

1

#2 opened 2 months ago by

nalimc

New activity in poolside/Laguna-S-2.1 2 months ago

Premature ending inside final answer after long thinking

#16 opened 2 months ago by

perelmanych

New activity in antirez/deepseek-v4-gguf 3 months ago

Running with recently merged llama.cpp PR

👍 6

6

#16 opened 3 months ago by

ubergarm

New activity in bartowski/DeepSeek-V4-Flash-GGUF 3 months ago

Follow up question results in complete mess

#4 opened 3 months ago by

perelmanych

New activity in WeiboAI/VibeThinker-3B 3 months ago

Really looking forward for 9B or 12B variants

4

#20 opened 3 months ago by

perelmanych

New activity in ubergarm/Kimi-K2-Thinking-GGUF 11 months ago

Definitely interested in this one!

🚀 2

25

#1 opened 11 months ago by

mtcl

New activity in xai-org/grok-2 about 1 year ago

Incorrect Model Uploaded

🤗👍 18

6

#8 opened about 1 year ago by

noteventhrice

New activity in zai-org/CC-Bench-trajectories about 1 year ago

Qwen3 coder version

#1 opened about 1 year ago by

perelmanych

New activity in sleepdeprived3/Llama-3.3-T3 about 1 year ago

Difference from other presets

#1 opened about 1 year ago by

perelmanych

New activity in bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF over 1 year ago

R1 32b is much worse than QwQ ...

22

#6 opened over 1 year ago by

mirek190

New activity in deepseek-ai/DeepSeek-R1-Distill-Llama-70B over 1 year ago

SFT (Non-RL) distillation is this good on a sub-100B model?

3

#2 opened over 1 year ago by

KrishnaKaasyap

New activity in mradermacher/Llama3-ChatQA-1.5-70B-GGUF over 2 years ago

IQ2_XS variant

1

#2 opened over 2 years ago by

perelmanych

New activity in lmsys/vicuna-33b-v1.3 almost 3 years ago

When we can expect vicuna variant of CodeLlama-2 34b model?

👍 1

#10 opened almost 3 years ago by

perelmanych

New activity in TheBloke/WizardCoder-Guanaco-15B-V1.1-GGML about 3 years ago

Can't load q5_1 model

3

#1 opened about 3 years ago by

perelmanych

New activity in anon8231489123/vicuna-13b-GPTQ-4bit-128g over 3 years ago

Error when using with web-ui "KeyError: 'model.layers.39.self_attn.q_proj.wf1'"

❤️ 1

16

#7 opened over 3 years ago by

TheFairyMan

New activity in anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g over 3 years ago

Error using ooba-gooba

👍 1

39

#6 opened over 3 years ago by

blueisbest