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.
DE
DeepSeek R1 Distill Qwen 1.5B GTAP v3 IQ2 XXS
DeepSeek · DuoNeural
Params1.78B
Context128K
Smallest0.6 GB
QW
Qwen2.5 0.5B Instruct
Qwen · DuoNeural
Params494M
Context32K
Smallest0.3 GB
DE
DeepSeek R1 Distill Qwen 1.5B GTAP v3 IQ2 M
DeepSeek · DuoNeural
Params1.78B
Context128K
Smallest0.7 GB
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · DuoNeural
Params7.62B
Context128K
Smallest3.1 GB
QW
Qwen3.5 9B
Qwen · DuoNeural
Params9.2B
Context256K
Q4_K_M5.8 GB
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · DuoNeural
Params7.62B
Context128K
Smallest2.8 GB
QW
Qwen2.5 Math 7B Instruct GTAP v3 IQ3 XXS
Qwen · DuoNeural
Params7.62B
Context4K
Smallest3.1 GB
QW
Qwen2.5 Coder 7B Instruct
Qwen · DuoNeural
Params7.62B
Context32K
Smallest3.1 GB
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · DuoNeural
Params8.03B
Context128K
Q4_K_M4.9 GB
QW
Qwen2.5 0.5B Instruct GTAP v3 IQ3 XXS
Qwen · DuoNeural
Params494M
Context32K
Smallest0.3 GB
DE
DeepSeek R1 Distill Qwen 1.5B GTAP v3 IQ3 XXS
DeepSeek · DuoNeural
Params1.78B
Context128K
Smallest0.8 GB
QW
Qwen2.5 Coder 7B Instruct GTAP v3 IQ3 XXS
Qwen · DuoNeural
Params7.62B
Context32K
Smallest3.1 GB
QW
Qwen2.5 Coder 3B SFT StructuredOutput
Qwen · DuoNeural
Params3.09B
Context32K
Q4_K_M1.9 GB
QW
Qwen2.5 Math 7B Instruct
Qwen · DuoNeural
Params7.62B
Context4K
Smallest3.1 GB
GE
Gemma 4 E2B It
Gemma · DuoNeural
Params4.65B
Context128K
Q4_K_M2.7 GB
LF
LFM2.5 2.6B
Lfm · DuoNeural
Params2.7B
Context128K
Q4_K_M1.7 GB
SM
Lattice 2 192M Poincare Base
SmolLM · DuoNeural
Params192M
Context512
Q4_K_M0.1 GB
GE
Gemma 4 12B It
Gemma · DuoNeural
Params11.9B
Context256K
Q4_K_M7.1 GB
LF
LFM2.5 1.2B Instruct
Lfm · DuoNeural
Params1.17B
Context125K
Q4_K_M0.7 GB
QW
Qwen2.5 1.5B Instruct GTAP v3 Q4 K M
Qwen · DuoNeural
Params1.54B
Context32K
Q4_K_M1.0 GB
GE
Archon Gemma 4 E4B v2
Gemma · DuoNeural
Params7.52B
Context128K
Q4_K_M5.3 GB
QW
Qwen2.5 Math 7B Instruct GTAP v3 Q4 K M
Qwen · DuoNeural
Params7.62B
Context4K
Q4_K_M4.7 GB
GH
GhostShell 4B
Ghostshell · DuoNeural
Params7.46B
Context128K
Q4_K_M5.3 GB
GE
Gemma 4 26B A4B It Abliterated
Gemma · DuoNeural
Params25.2B
Context256K
Q4_K_M16.8 GB
QW
Qwen2.5 0.5B Instruct GTAP v3 Q4 K M
Qwen · DuoNeural
Params494M
Context32K
Q4_K_M0.4 GB
QW
Qwen2.5 Math NeuralMath 7B
Qwen · DuoNeural
Params7.62B
Context4K
Q4_K_M4.7 GB
LF
LFM2.5 8B A1B TAP DPQ 3.5bpw
Lfm · DuoNeural
Params8.47B
Context125K
Smallest3.6 GB
SM
Sub Lattice v3 18M Poincare Hybrid
SmolLM · DuoNeural
Params18M
Context512
Q4_K_M0.0 GB
GE
Archon Gemma 4 E4B
Gemma · DuoNeural
Params7.52B
Context128K
Q4_K_M5.3 GB
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · DuoNeural
Params7.62B
Context128K
Q4_K_M4.7 GB