GGUF models by build-small-hackathon

41 GGUF models quantized by build-small-hackathon on Hugging Face. Sizes run from 11M to 31.6B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
NE
Nemotron nano 4b escape room
Nemotron · build-small-hackathon
Params3.97B
Context1024K
Q4_K_M2.8 GB
ReasoningTool use
GE
gemma 4 cal
Gemma · build-small-hackathon
Params7.52B
Context128K
Q4_K_M5.3 GB
ReasoningTool useVision
LL
lolaby llama 3b
Llama · build-small-hackathon
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
MI
MiniCPM5 1B lost frequency radio
MiniCPM · build-small-hackathon
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use
NE
nemotron car diagnostics
Nemotron · build-small-hackathon
Params3.97B
Context1024K
Q4_K_M2.8 GB
CodingReasoningTool use
GE
mafia gemma 4 12B it
Gemma · build-small-hackathon
Params11.9B
Context256K
Smallest12.7 GB
ReasoningVision
QW
job searcher qwen3 8B
Qwen · build-small-hackathon
Params44M
Context40K
Q4_K_M5.0 GB
Reasoning
MI
professor pip minicpm5 1b
MiniCPM · build-small-hackathon
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use
QW
lfed qwen2.5 coder 7b sql
Qwen · build-small-hackathon
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
GE
Gemma 26B A4B VisualNovel
Gemma · build-small-hackathon
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
MI
compliment forest minicpm5 1b
MiniCPM · build-small-hackathon
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use
QW
lfed qwen2.5 coder 14b sql
Qwen · build-small-hackathon
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
MI
AI Puppet Theater MiniCPM5 Actor
MiniCPM · build-small-hackathon
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use
QW
codeflow qwen 3 finetuning
Qwen · build-small-hackathon
Params30.5B
Context256K
Smallest15.9 GB
CodingTool use
MI
gigscan minicpm v
MiniCPM · build-small-hackathon
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
MI
MiniCPM4 8B PaperProf
MiniCPM · build-small-hackathon
Params8.19B
Context32K
Q4_K_M5.0 GB
GGUF
MI
mind of tashi micro sft
Mind · build-small-hackathon
Params390M
Context256K
Q4_K_M0.3 GB
ReasoningTool use
MI
tianwen minicpm5 1b
MiniCPM · build-small-hackathon
Params1.08B
Context128K
Smallest2.2 GB
ReasoningTool use
MI
MiniCPM4.1 8B PaperProf
MiniCPM · build-small-hackathon
Params8.19B
Context64K
Q4_K_M5.0 GB
Reasoning
MI
mind of tashi micro grpo
Mind · build-small-hackathon
Params390M
Context256K
Q4_K_M0.3 GB
ReasoningTool use
MI
minicpm5 1b indian fmcg normalizer
MiniCPM · build-small-hackathon
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use
MI
elysium MiniCPM V 4.6 F16
MiniCPM · build-small-hackathon
Params1.01B
Context256K
Smallest2.0 GB
ReasoningTool useVision
SO
solace llm
Solace · build-small-hackathon
Params11M
Context128K
Q4_K_M0.7 GB
GGUF
QW
HF Knight Qwen2.5 1.5B Instruct
Qwen · build-small-hackathon
Params1.54B
Context32K
Smallest1.6 GB
RoleplayTool use
GE
agenda parser high
Gemma · build-small-hackathon
Params25.2B
Context256K
Smallest26.9 GB
ReasoningTool use
PH
phase 3
Phase · build-small-hackathon
Params31.6B
Context1024K
Smallest33.6 GB
GGUF
DE
Deku Merged
Deku · build-small-hackathon
Params494M
Context32K
Smallest0.5 GB
Tool use
QW
limp mode leap1
Qwen · build-small-hackathon
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
GE
agenda parser lite
Gemma · build-small-hackathon
Params7.46B
Context128K
Smallest8.0 GB
ReasoningTool use
MI
paint match minicpm
MiniCPM · build-small-hackathon
Params752M
Context256K
Smallest0.6 GB
ReasoningTool useVision

About build-small-hackathon on Hugging Face

build-small-hackathon has published 41 GGUF models that ggufmodels.com tracks, across families such as MiniCPM, Qwen and Gemma. The most downloaded are Nemotron nano 4b escape room, gemma 4 cal and lolaby llama 3b.

The quants build-small-hackathon publishes most often are Q4_K_M (25), Q8_0 (10), F16 (9) and Q6_K (1). Their Q4_K_M files range from 0.3 to 18.7 GB. Parameter counts run from 11M to 31.6B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has build-small-hackathon published?

41 models are listed here, mainly from the MiniCPM, Qwen and Gemma families. The most downloaded is Nemotron nano 4b escape room.

Which quants does build-small-hackathon publish?

The most common are Q4_K_M (25 models), Q8_0 (10 models), F16 (9 models) and Q6_K (1 models).

Keep browsing