Jaap Buurman

Mushoz's activity

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

New activity in AesSedai/Qwen3.8-Flash-Next-GGUF 9 days ago

Keep ngram tensors unquantized

15

#2 opened 15 days ago by

Mushoz

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 17 days ago

Measured: ngram-map-k beats ngram-mod; ngram-cache costs -24% on prose (5060 Ti 16GB + 128GB)

🚀👍 6

2

#34 opened 17 days ago by

solarkyle

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF about 1 month ago

DSpark enables DeepSeek to run 2x Faster!

🤗🔥 2

5

#36 opened about 1 month ago by

danielhanchen

New activity in tarruda/DeepSeek-V4-Flash-GGUF 2 months ago

Missing tensors?

5

#1 opened 2 months ago by

Mushoz

New activity in AesSedai/Step-3.7-Flash-GGUF 3 months ago

PPQ(Q)/PPL(base) and KLD seems significantly worse than Step 3.5 Flash

👀 1

23

#2 opened 4 months ago by

tarruda

New activity in QuantPasture/Step-3.5-Flash-GGUF 7 months ago

Great custom quant!

2

#1 opened 7 months ago by

Mushoz

New activity in unsloth/gpt-oss-120b-GGUF about 1 year ago

Gpt-oss updated Configure `<|call|>` as an EOS token

1

#10 opened about 1 year ago by

pipilok

New activity in unsloth/Devstral-Small-2507-GGUF about 1 year ago

Unsloth template changes broke tool calling

8

#1 opened about 1 year ago by

squid2

New activity in mradermacher/Qwen3-0.6B-Base-i1-GGUF over 1 year ago

IQ4_XS size seems low?

11

#1 opened over 1 year ago by

Mushoz

New activity in unsloth/Qwen3-30B-A3B-GGUF over 1 year ago

Latest updates?

👍 12

8

#10 opened over 1 year ago by

Dampfinchen

New activity in bartowski/THUDM_GLM-4-32B-0414-GGUF over 1 year ago

llama.cpp fixes have just been merged

🤗 2

21

#5 opened over 1 year ago by

Mushoz

New activity in agentica-org/DeepCoder-14B-Preview over 1 year ago

This is unbelievable! Bravo team 👏

🤗 1

21

#2 opened over 1 year ago by

yunomioni

New activity in google/gemma-3-12b-it-qat-q4_0-gguf over 1 year ago

Token issue? <start_of_turn> split into multiple tokens

5

#3 opened over 1 year ago by

mw55a

New activity in FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview over 1 year ago

Model Issue

🤝 1

5

#1 opened over 1 year ago by

YOYO-AI

New activity in bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF almost 2 years ago

IQ4_NL

6

#3 opened almost 2 years ago by

Mushoz

IQ4_NL

6

#3 opened almost 2 years ago by

Mushoz

IQ4_NL

6

#3 opened almost 2 years ago by

Mushoz