Slavik

SlavikF's activity

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

New activity in huihui-ai/Huihui-DeepSeek-V4-Flash-abliterated-GGUF about 8 hours ago

Performance report: Q3_K_S on RTX 5090 + 384GB DDR5: 15 t/s

👍 1

#2 opened about 8 hours ago by

SlavikF

New activity in lovesenko/DeepSeek-V4-Flash-DSpark-Abliterated about 16 hours ago

Do you plan to offer this model in GGUF?

👀 1

2

#1 opened 8 days ago by

Nerdsking

New activity in unsloth/GLM-5.2-GGUF about 17 hours ago

Performance report UD-Q3_K_XL on RTX 5090 + 384GB DDR5: 4 t/s

#14 opened about 17 hours ago by

SlavikF

New activity in unsloth/gemma-4-E4B-it-qat-GGUF 9 days ago

Performance report: 55 t/s on RTX 4060

👍 1

1

#4 opened 9 days ago by

SlavikF

New activity in unsloth/MiniMax-M3-GGUF about 1 month ago

5-bit MiniMax M3 running locally on a single M3 Ultra 512GB via Unsloth!

👍🔥 3

6

#3 opened about 1 month ago by

danielhanchen

New activity in MiniMaxAI/MiniMax-M3 about 1 month ago

Is MTP supported?

3

#5 opened about 1 month ago by

SlavikF

New activity in Qwen/Qwen3.6-27B-FP8 about 2 months ago

Performance report on RTX 4090D (48GB VRAM): 40 t/s

4

#11 opened 2 months ago by

SlavikF

New activity in unsloth/Qwen3.6-27B-MTP-GGUF 2 months ago

Report: 56 t/s on RTX 4090D (48GB VRAM) with UD-Q6_K_XL

3

#25 opened 2 months ago by

SlavikF

New activity in unsloth/Qwen3.6-27B-GGUF 2 months ago

Report: 30 t/s on RTX 4090D (48GB VRAM) with UD-Q6_K_XL

🤝 5

4

#7 opened 3 months ago by

SlavikF

New activity in unsloth/Nemotron-3-Nano-30B-A3B-GGUF 3 months ago

Q4_K_XL on RTX 4090D with 1M context: ~70 t/s

#14 opened 3 months ago by

SlavikF

1 M‑token context running smoothly at ~25 t/s on a 12 GB RX 6700 XT is nothing short of impressive.

👍😔 4

3

#6 opened 7 months ago by

Jbulger82

New activity in unsloth/gemma-4-31B-it-GGUF 3 months ago

Apr 11: Updated with Google chat template fixes + more

👍❤️ 17

20

#16 opened 3 months ago by

danielhanchen

New activity in Qwen/Qwen3.5-Omni-Online-Demo 4 months ago

What "Realtime" means?

#2 opened 4 months ago by

SlavikF

New activity in ai-sage/GigaChat3.1-10B-A1.8B-GGUF 4 months ago

Performance report for Q6_k on RTX 3090 and RTX 4090D

1

#6 opened 4 months ago by

SlavikF

New activity in unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF 4 months ago

Performance report: 44-62 t/s with 72GB VRAM and 512k context

#6 opened 4 months ago by

SlavikF

New activity in unsloth/Qwen3.5-122B-A10B-GGUF 4 months ago

Performance report for UD-Q4_K_XL with 72GB VRAM: 65 t/s

🔥👍 3

5

#3 opened 5 months ago by

SlavikF

Updates needed for this quants?

👀 6

8

#9 opened 5 months ago by

SlavikF

New activity in unsloth/Qwen3.5-397B-A17B-GGUF 5 months ago

Q3_K_XL works surprisingly fast for 3x3090 + 128 ram

🔥 8

7

#4 opened 5 months ago by

fizzacles

How to choose MXFP4 vs Q4_K_XL on CPU + CUDA

2

#1 opened 5 months ago by

SlavikF

New activity in Qwen/Qwen3-Coder-Next-GGUF 5 months ago

Performance report with 2 GPUs: 85 t/s

👍 4

1

#1 opened 5 months ago by

SlavikF