GGUF models by Flexan

72 GGUF models quantized by Flexan on Hugging Face. Sizes run from 11M to 8.19B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
BI
1kz Bigcodemax
Bigcodemax · Flexan
Params7.3B
Context64K
Q4_K_M4.5 GB
CodingReasoning
QW
kshitijthakkar qwen3.5 moe 0.87B d0.8B
Qwen · Flexan
Params1.01B
Context256K
Q4_K_M0.8 GB
ReasoningTool useVision
BL
Blake XTM Arc T0
Blake · Flexan
Params7.24B
Context32K
Q4_K_M4.4 GB
ReasoningTool use
NO
Nopenet Nope Edge
Nope · Flexan
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
HD
Novaciano HDP 1B
Hdp · Flexan
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
KA
NoesisLab Kai 0.35B Instruct
Kai · Flexan
Params362M
Context8K
Q4_K_M0.3 GB
Reasoning
PH
Blake XTM Arc 3B V1
Phi · Flexan
Params2.78B
Context2K
Q4_K_M1.7 GB
ReasoningTool use
QW
RAS1981 Qwen3 Turn Detector Merged
Qwen · Flexan
Params596M
Context40K
Q4_K_M0.4 GB
ReasoningTool use
QW
Naimulislam864 Qwen2.5 0.5B Tool Calling
Qwen · Flexan
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
BL
Flexan Blake Haiku 1
Blake · Flexan
Params596M
Context40K
Q4_K_M0.4 GB
ReasoningTool use
NO
Nopenet Nope Edge Mini
Nope · Flexan
Params2.03B
Context40K
Q4_K_M1.3 GB
ReasoningTool use
BL
Blake XTM Arc
Blake · Flexan
Params7.24B
Context32K
Q4_K_M4.4 GB
ReasoningTool use
LO
LocoreMind LocoOperator 4B
Locooperator · Flexan
Params4.02B
Context256K
Q4_K_M2.5 GB
CodingTool use
NO
Nopenet Nope Edge Mini
Nope · Flexan
Params2.03B
Context40K
Q4_K_M1.3 GB
ReasoningTool use
QW
Flexan FoxyzGPT X1.1 1.7B
Qwen · Flexan
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
HA
Hamzah0Asadullah TinyRP 0.8B
Hamzah · Flexan
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningRoleplayTool use
QW
Davidheineman Davids Email Llm
Qwen · Flexan
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
PO
StentorLabs Portimbria 150M
Portimbria · Flexan
Params176M
Context4K
Q4_K_M0.1 GB
CodingTool use
LF
Andy-Feather-V2-700m
Lfm · Flexan
Params742M
Context125K
Q4_K_M0.5 GB
Tool use
DQ
DQN Labs dqnMath v0.1 3B HF
Dqnmath · Flexan
Params3.43B
Context256K
Q4_K_M2.1 GB
Tool use
HU
Flexan HumanPet X1 1.7B
Humanpet · Flexan
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
NP
Novaciano NPC 1B PERVERTIDO
Npc · Flexan
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
LL
Fredtt3 LLaDA 100M Test
Llada · Flexan
Params310M
Context4K
Q4_K_M0.2 GB
GGUF
SY
Syko818121 SykoLLM V4.6 CodeX Beta
Sykollm · Flexan
Params338M
Context1K
Q4_K_M0.2 GB
GGUF
QU
QuantaSparkLabs Quantum X
Quantum · Flexan
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
UL
Ulamai Ulam 1 Small
Ulam · Flexan
Params3.09B
Context128K
Q4_K_M1.9 GB
ReasoningTool use
NO
Nopenet Nope Edge
Nope · Flexan
Params2.03B
Context40K
Q4_K_M1.3 GB
ReasoningTool use
MI
FoxyzGPT 1.1 7B
Mistral · Flexan
Params7.25B
Context32K
Q4_K_M4.4 GB
Tool use
DQ
DQN Labs dqnMath v0.2 3.8B HF
Dqnmath · Flexan
Params3.84B
Context128K
Q4_K_M2.5 GB
CodingTool use
PI
RthItalia PINDARO AI CODE
Pindaro · Flexan
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding

About Flexan on Hugging Face

Flexan has published 72 GGUF models that ggufmodels.com tracks, across families such as Qwen, Nope and Stage. The most downloaded are 1kz Bigcodemax, kshitijthakkar qwen3.5 moe 0.87B d0.8B and Blake XTM Arc T0.

The quants Flexan publishes most often are Q4_K_M (72), Q2_K (72), F16 (72) and Q8_0 (71). Their Q4_K_M files range from 0.0 to 5.0 GB. Parameter counts run from 11M to 8.19B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has Flexan published?

72 models are listed here, mainly from the Qwen, Nope and Stage families. The most downloaded is 1kz Bigcodemax.

Which quants does Flexan publish?

The most common are Q4_K_M (72 models), Q2_K (72 models), F16 (72 models) and Q8_0 (71 models).

Keep browsing