👋 Open to Work

Kaloyan Nikolov

sleepyeldrazi

21 1 6

https://git.kokoham.com/sleepy

AI & ML interests

ML engineer working on LLM inference and training. Finalizing my M.Sc. Computer Science @ RWTH Aachen. Currently focusing on DGX Spark models/frameworks. Contact: konik98@gmail.com

Recent Activity

new activity 4 days ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:Quick Comparison: ISTA-DASLab GSQ-RCO-IQ3_XXS vs unsloth UD-IQ4_XS on 4070Ti Super 16G + 64G RAM

upvoted a collection 8 days ago

GSQ-RCO-GGUF

new activity 19 days ago

sleepyeldrazi/Ornith-1.5-REAP-20B-A3B-GGUF:List of pruned experts

View all activity

Organizations

None yet

New activity in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF 4 days ago

Quick Comparison: ISTA-DASLab GSQ-RCO-IQ3_XXS vs unsloth UD-IQ4_XS on 4070Ti Super 16G + 64G RAM

#18 opened 6 days ago by

BipedalBit

New activity in sleepyeldrazi/Ornith-1.5-REAP-20B-A3B-GGUF 19 days ago

List of pruned experts

#1 opened 24 days ago by

kdrapel

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 28 days ago

Early report running it on a DGX Spark, 4 concurrent @ 256k bf16 with SSD offload

👍 7

#31 opened 28 days ago by

sleepyeldrazi

New activity in quimmedes/Qwen3.8-Flash-Next-MTP-GGUF 28 days ago

BF16 Missing currently

#1 opened 28 days ago by

sleepyeldrazi

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 28 days ago

NVME vs Optane?

#29 opened 28 days ago by

AndyFaceHugger

Is it possible to offload n-gram to an NVMe SSD?

👀🚀 31

#11 opened 29 days ago by

lingyezhixing

New activity in z-lab/Qwen3.8-27B-DFlash2 about 1 month ago

Yet to see any gains from DFlash

👍 11

#3 opened about 1 month ago by

Dnonmi

New activity in incoai/Qwen3.8-27B-DFlash2 about 1 month ago

FP8

#2 opened about 1 month ago by

vcerny

New activity in poolside/Laguna-S-2.1 about 1 month ago

BenchMAXXXED

➕ 2

#28 opened about 2 months ago by

TawusGames

New activity in Qwen/Qwen3.8-27B about 1 month ago

Exploring ThinkingCap fine-tunes for Qwen 3.8: Is it still necessary with native `reasoning_effort`?

👍 4

#106 opened about 1 month ago by

icognito

How can I run this well on an RTX 5070 ti?

#36 opened about 1 month ago by

theonerm2

New activity in Qwen/Qwen3.8-2.4T-A95B about 1 month ago

Text-only? Plans for multimodal release?

👀😔 5

#7 opened about 1 month ago by

sleepyeldrazi

New activity in poolside/Laguna-S-2.1-NVFP4 about 2 months ago

Reproducible Laguna S 2.1 NVFP4 runaway reasoning: output budget scales 2K → 16K with 12/12 length exhaustion and no final answer

👀👍 8

#16 opened about 2 months ago by

darkmatter2222

Still looping after update - details inside

👀 2

#10 opened 2 months ago by

cbert33

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

Model is decent, its faster than Qwen and pretty close on real world tool calls

❤️👀 3

#22 opened 2 months ago by

Jakaryun

New activity in prism-ml/Ternary-Bonsai-27B-gguf 2 months ago

MOE or changing to A3B

#43 opened 2 months ago by

Tom-Neverwinter

New activity in Qwen/Qwen-AgentWorld-35B-A3B 3 months ago

Awesome model

👍❤️ 16

#2 opened 3 months ago by

pengzhi27

New activity in lordx64/Qwable-v1 3 months ago

Distilled Reasoning or Just XML Cosplay?

🔥 2

#2 opened 3 months ago by

SuperSonnix71

New activity in google/gemma-4-12B-it 4 months ago

File path upper case issue

#8 opened 4 months ago by

sleepyeldrazi

New activity in unsloth/gemma-4-12b-it-GGUF 4 months ago

File path case issue

#5 opened 4 months ago by

sleepyeldrazi

Kaloyan Nikolov

AI & ML interests

Recent Activity

Organizations

sleepyeldrazi's activity

Quick Comparison: ISTA-DASLab GSQ-RCO-IQ3_XXS vs unsloth UD-IQ4_XS on 4070Ti Super 16G + 64G RAM

List of pruned experts

Early report running it on a DGX Spark, 4 concurrent @ 256k bf16 with SSD offload

BF16 Missing currently

NVME vs Optane?

Is it possible to offload n-gram to an NVMe SSD?

Yet to see any gains from DFlash

FP8

BenchMAXXXED

Exploring ThinkingCap fine-tunes for Qwen 3.8: Is it still necessary with native `reasoning_effort`?

How can I run this well on an RTX 5070 ti?

Text-only? Plans for multimodal release?

Reproducible Laguna S 2.1 NVFP4 runaway reasoning: output budget scales 2K → 16K with 12/12 length exhaustion and no final answer

Still looping after update - details inside

Model is decent, its faster than Qwen and pretty close on real world tool calls

MOE or changing to A3B

Awesome model

Distilled Reasoning or Just XML Cosplay?

File path upper case issue

File path case issue