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
QW
Lattice 6 Prometheus v2 HeptaCap
Qwen · DuoNeural
Params406M
Context512
Smallest0.3 GB
GGUF
QW
Qwen3.8 27B
Qwen · DuoNeural
Params27.3B
Context256K
Q4_K_M16.8 GB
Coding
SM
Lattice 4E Lorentz Holographic 253M Instruct
SmolLM · DuoNeural
Params253M
Context512
Q4_K_M0.2 GB
GGUF
PH
Phi 4 Mini Reasoning Abliterated
Phi · DuoNeural
Params3.84B
Context128K
Q4_K_M2.5 GB
ReasoningTool use
GE
Gemma 4 E4B Claude Abliterated
Gemma · DuoNeural
Params7.52B
Context128K
Q4_K_M5.3 GB
CodingReasoningTool use
LL
Llama 3.1 8B Instruct
Llama · DuoNeural
Params8.03B
Context128K
Smallest3.3 GB
Tool use
QW
Qwen3.5 9B
Qwen · DuoNeural
Params9.2B
Context256K
Q4_K_M5.8 GB
Reasoning
QW
Qwen2.5 Coder 7B Instruct GTAP v3 IQ2 M
Qwen · DuoNeural
Params7.62B
Context32K
Smallest2.8 GB
CodingTool use
QW
Qwen3.5 9B Abliterated
Qwen · DuoNeural
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
QW
Qwen3.6 35B A3B Code imatrix
Qwen · DuoNeural
Params34.7B
Context256K
Q4_K_M21.2 GB
CodingReasoningTool use
QW
Qwen3 4B
Qwen · DuoNeural
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
IN
InternLM3 8B Instruct
InternLM · DuoNeural
Params8.8B
Context32K
Q4_K_M5.4 GB
GGUF
MI
Ministral 8B Instruct
Mistral · DuoNeural
Params8.02B
Context32K
Q4_K_M4.9 GB
Tool use
XL
CrystalCall v5 DCG
Xlam · DuoNeural
Params116M
Context512
Smallest0.1 GB
GGUF
GE
Gemma 4 E4B It
Gemma · DuoNeural
Params7.5B
Context128K
Q4_K_M4.4 GB
GGUF
QW
Qwen2.5 Coder 7B Instruct
Qwen · DuoNeural
Params7.62B
Context32K
Smallest2.8 GB
CodingTool use
QW
Qwen3.5 9B
Qwen · DuoNeural
Params9.2B
Context256K
Smallest3.7 GB
ReasoningTool use
QW
Qwen3.5 9B
Qwen · DuoNeural
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool use
QW
Qwen3.5 9B
Qwen · DuoNeural
Params9.2B
Context256K
Smallest4.1 GB
ReasoningTool use
QW
Qwen2.5 7B Instruct
Qwen · DuoNeural
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
QW
Qwen/Qwen3.5-9B
Qwen · DuoNeural
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
QW
Qwen2.5 Coder 7B Instruct GTAP v3 Q4 K M
Qwen · DuoNeural
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
XL
CrystalCall v2 Poincare 7L 91M
Xlam · DuoNeural
Params91M
Context512
Smallest0.1 GB
GGUF
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · DuoNeural
Params7.62B
Context128K
Smallest2.3 GB
ReasoningTool use
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · DuoNeural
Params8.03B
Context128K
Smallest3.3 GB
ReasoningTool use
QW
Qwen2.5 Coder 7B Instruct GTAP v3 IQ2 XXS
Qwen · DuoNeural
Params7.62B
Context32K
Smallest2.3 GB
CodingTool use
QW
Qwen3 8B
Qwen · DuoNeural
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · DuoNeural
Params1.78B
Context128K
Smallest0.8 GB
ReasoningTool use
LL
Llama 3.1 8B Instruct GTAP v3 IQ3 XXS
Llama · DuoNeural
Params8.03B
Context128K
Smallest3.3 GB
Tool use
MI
Mistral 7B Instruct v0.3
Mistral · DuoNeural
Params7.25B
Context32K
Q4_K_M4.4 GB
Tool use

Keep browsing