GGUF models by DuoNeural

120 GGUF models quantized by DuoNeural on Hugging Face. Sizes run from 17M to 34.7B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
NE
Nemotron 3 Nano 4b
Nemotron · DuoNeural
Params3.97B
Context1024K
Q4_K_M2.8 GB
ReasoningTool use
LF
LFM2.5 230M
Lfm · DuoNeural
Params230M
Context125K
Q4_K_M0.2 GB
ReasoningTool use
LF
LFM2.5 350M
Lfm · DuoNeural
Params354M
Context125K
Q4_K_M0.2 GB
ReasoningTool use
GE
google/gemma-4-E2B-it
Gemma · DuoNeural
Params4.65B
Context128K
Q4_K_M3.4 GB
CodingReasoningTool use
LF
LFM2.5 8B A1B TAP DPQ 2.72bpw
Lfm · DuoNeural
Params8.47B
Context125K
Smallest2.9 GB
ReasoningTool use
QW
Lattice 1 107M Poincare Preview
Qwen · DuoNeural
Params107M
Context512
Q4_K_M0.1 GB
GGUF
SM
Sub Lattice 17M Poincare Instruct
SmolLM · DuoNeural
Params17M
Context512
Q4_K_M0.0 GB
GGUF
SM
Lattice 4 Josephson 253M Poincare Instruct
SmolLM · DuoNeural
Params253M
Context512
Q4_K_M0.2 GB
GGUF
LL
Llama 3.1 8B Instruct GTAP v3 Q4 K M
Llama · DuoNeural
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · DuoNeural
Params8.03B
Context128K
Smallest2.4 GB
ReasoningTool use
QW
Qwen2.5 7B Instruct GTAP Q4 K M
Qwen · DuoNeural
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
EN
ml ai engineer 7b
Engineer · DuoNeural
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
QW
Qwen2.5 1.5B Instruct
Qwen · DuoNeural
Params1.54B
Context32K
Smallest0.7 GB
Tool use
SM
Lattice 4 Nexus 253M Poincare Instruct
SmolLM · DuoNeural
Params253M
Context512
Q4_K_M0.2 GB
GGUF
SM
Lattice 3 Synapse 192M Poincare Instruct
SmolLM · DuoNeural
Params192M
Context512
Q4_K_M0.1 GB
GGUF
QW
Qwen2.5 1.5B Instruct GTAP v3 IQ3 XXS
Qwen · DuoNeural
Params1.54B
Context32K
Smallest0.7 GB
Tool use
GE
Gemma 4 26B A4B It
Gemma · DuoNeural
Params25.2B
Context256K
Smallest13.3 GB
ReasoningTool use
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · DuoNeural
Params8.03B
Context128K
Smallest2.9 GB
ReasoningTool use
QW
Qwen3.8 27B TAP DPQ 2.72bpw
Qwen · DuoNeural
Params27.3B
Context256K
Smallest8.9 GB
ReasoningTool use
QW
Qwen3.5 9B
Qwen · DuoNeural
Params9.2B
Context256K
Smallest4.4 GB
ReasoningTool use
GE
Gemma4 31B IT Abliterated
Gemma · DuoNeural
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningTool use
QW
Qwen2.5 7B Instruct
Qwen · DuoNeural
Params7.62B
Context32K
Smallest3.1 GB
CodingTool use
AD
AdQWENistrator 9B
Adqwenistrator · DuoNeural
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
TR
translategemma 4b it LiteRT
Translategemma · DuoNeural
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
PH
Phi 3.5 Mini Instruct
Phi · DuoNeural
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
QW
Qwen2.5 1.5B Instruct LiteRT
Qwen · DuoNeural
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
SM
SmolLM2 1.7B Instruct LiteRT
SmolLM · DuoNeural
Params1.71B
Context8K
Q4_K_M1.1 GB
GGUF
TU
TurboGemma4E2B
Turbogemma · DuoNeural
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningTool use
SM
SmolLM2 135M Instruct LiteRT
SmolLM · DuoNeural
Params135M
Context8K
Q4_K_M0.1 GB
GGUF
ME
medgemma 1.5 4b it LiteRT
Medgemma · DuoNeural
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF

Keep browsing