Avi Fenesh PRO

Avifenesh's activity

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

New activity in unsloth/Qwen3.8-27B-GGUF about 16 hours ago

DFlash2?

👀 5

1

#79 opened about 23 hours ago by

guarism0

NVFP4/MXFP4 GGUF Version?

👍 3

2

#75 opened 1 day ago by

CYISNOTHERE

New activity in ornith-ai/Ornith-1.5-35B-A3B about 19 hours ago

Unsloth GGUF's please

1

#3 opened about 23 hours ago by

jlindeberg

New activity in ornith-ai/Ornith-1.5-35B-A3B-GGUF about 19 hours ago

MTP Support

🚀 8

2

#2 opened 1 day ago by

DefaultDF

New activity in Qwen/Qwen3.8-27B 2 days ago

MTP (SPEC_DRAFT_N_MAX) leads to Nvidia RC Watchdog killing the kernel, llama.cpp calls SIGABRT

➕ 1

5

#122 opened 3 days ago by

Nosepicker3

New activity in google/gemma-4-31B-it 2 days ago

Gemma-4-31B-it occasionally emits <turn|> token when served via vLLM, causing failures when using it with GitHub Copilot Custom Model Provider

3

#138 opened 22 days ago by

aygupt

New activity in unsloth/Qwen3.8-27B-GGUF 3 days ago

Small Quants with integrated MTP dont make sense

👍 4

3

#37 opened 6 days ago by

HuggingButtt

New activity in Qwen/Qwen3.8-27B 3 days ago

qwen3.8-27b on one pro 6000: 140 tok/s, day after release

7

#101 opened 5 days ago by

Avifenesh

New activity in Qwen/Qwen3.8-27B 4 days ago

MTP speculation is net-negative under Ollama's GGUF path, strongly positive under MLX (measured on M4 Pro)

5

#80 opened 5 days ago by

OtsoaD

New activity in Avifenesh/Qwen3.8-27B-NVFP4-MTP-GGUF 5 days ago

live api

#2 opened 5 days ago by

Avifenesh

New activity in Qwen/Qwen3.8-27B 5 days ago

Tested the model (locally) on coding and agentic work

👍 1

1

#99 opened 5 days ago by

curiousily

MTP support in 🤗️ `transformers`

1

#56 opened 6 days ago by

crumb

New activity in unsloth/Qwen3.8-27B-GGUF 5 days ago

MTP?

15

#12 opened 6 days ago by

HuggingButtt

New activity in Qwen/Qwen3.8-27B 5 days ago

After waiting 49 minutes and 16 seconds while the model was still thinking, I'm simply giving up...

🧠👀 3

12

#92 opened 5 days ago by

MrDevolver

we quantized Qwen3.8-27B and compared it with community GGUFs on 4x RTX 5090!

🚀 6

5

#65 opened 6 days ago by

d4nnyy

DFlash draft model instead of MTP one

👍 2

9

#54 opened 6 days ago by

artden111

Qwen3.8-27B on RTX 5090 (SM120): the fused GDN decode kernel is unreachable, twice

🚀 2

2

#51 opened 6 days ago by

kakrotto

New activity in Avifenesh/Qwen3.8-27B-NVFP4-MTP-GGUF 6 days ago

Q5K-mtp Fits 100% VRAM on Dual 5060TI-16gb , and Results from Google Cybersecurity Course 1 tests

2

#1 opened 6 days ago by

AIconjured

New activity in unsloth/Qwen3.8-27B-NVFP4 6 days ago

Why no NVFP4 GGUF?

👍👀 9

5

#6 opened 6 days ago by

mattzink