🔄 In a Training Loop
Pasha
AI & ML interests
Probabilities
Recent Activity
liked a model about 2 hours ago
unsloth/Qwen3.8-27B-GGUF liked a dataset 2 days ago
RMT-team/babilong liked a model 3 days ago
bottlecapai/ThinkingCap-Qwen3.6-27BOrganizations
A simple math
1
#1 opened about 1 month ago
by
rahul7star
Speed when CPU-only?
8
#51 opened 12 days ago
by
TriAxp
Update metadata (tokenizer.ggml.model)
#23 opened 9 days ago
by
abudahm
VLLM serve is not working
3
#19 opened 21 days ago
by
codegood
Ollama 500 error loading Bonsai-27B GGUF (dspark architecture)
➕👍 2
4
#11 opened about 1 month ago
by
amdeld
LM Studio
👍 1
6
#17 opened 30 days ago
by
Melektavus22
Beware of the kv_cache params!
😔🔥 7
19
#36 opened about 1 month ago
by
aaron-newsome
Error in tokenizer
1
#16 opened about 1 month ago
by
Ragoon35
Ternary-Bonsai-27B-mlx-2bit slow on macbook 4 pro with oMLX
2
#2 opened about 1 month ago
by
nps798
community_gpqa_diamond
#28 opened about 1 month ago
by
christopher-oneill
Unable to get D-Spark Q4_1 working with Q2_0 Model file
9
#11 opened about 1 month ago
by
AceTheUnfazed
Issue with using "raw" benchmark scores for intelligence density
🔥 2
3
#7 opened about 1 month ago
by
Green-Sky
Add community evaluation results for GSM8K, AIME_2026, MMMU_PRO
#27 opened about 1 month ago
by
nielsr
Add community evaluation results for AIME_2026, GSM8K, MMMU_PRO
#12 opened about 1 month ago
by
nielsr
Unable to pull Q8_0
2
#26 opened about 1 month ago
by
ly2025
Benchmark: 27B Q2_0 vs Qwen3.6-27B IQ2_XXS on one RTX 5060 Ti 16 GB (quality@budget, speed, VRAM, energy)
❤️🔥 7
1
#24 opened about 1 month ago
by
Astezelex
dpark or MTP command line
8
#6 opened about 1 month ago
by
PhilippeEiffel
What parameters can generally be set in LM Studio to achieve optimal performance?
4
#18 opened about 1 month ago
by
pymo
Script to convert PQ2_0 to Q2_0 - code in-line here
2
#20 opened about 1 month ago
by
sfrav