GGUF models by duyntnet

305 GGUF models quantized by duyntnet on Hugging Face. Sizes run from 163M to 35B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
PH
Phi 3 mini 128k instruct imatrix
Phi · duyntnet
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
AY
Aya Expanse 8b
Aya · duyntnet
Params8B
Context8K
Q4_K_M5.1 GB
GGUF
GR
Granite 8b Code Instruct
Granite · duyntnet
Params8.05B
Context4K
Q4_K_M4.9 GB
Coding
TI
TinyLlama 1.1B Chat v1.0 imatrix
Tinyllama · duyntnet
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
DE
deepseek-coder-1.3b-instruct
DeepSeek · duyntnet
Params1.35B
Context16K
Q4_K_M0.9 GB
Coding
TH
TheSpice-7b-FT-v0.3.1
Thespice · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
PH
Phi 3.5 Mini Instruct
Phi · duyntnet
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
GE
Gemma 2 9b It
Gemma · duyntnet
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
QW
Qwen1.5 MoE A2.7B Chat
Qwen · duyntnet
Params14.3B
Context32K
Q4_K_M9.5 GB
GGUF
IN
Internlm2_5 7b Chat 1m
InternLM · duyntnet
Params7.74B
Context256K
Q4_K_M4.7 GB
GGUF
YI
Yi-6B-200K
Yi · duyntnet
Params6.06B
Context195K
Q4_K_M3.7 GB
GGUF
PH
Phi 3 medium 128k instruct imatrix
Phi · duyntnet
Params14B
Context128K
Q4_K_M8.6 GB
GGUF
PH
Phi 3 mini 4k instruct imatrix
Phi · duyntnet
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF
LL
Nous-Hermes-Llama2-13b
Llama · duyntnet
Params13B
Context4K
Q4_K_M7.9 GB
Tool use
LL
Yarn-Llama-2-7b-128k
Llama · duyntnet
Params6.74B
Context128K
Q4_K_M4.1 GB
GGUF
QW
Qwen2.5 Coder 7B
Qwen · duyntnet
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
DE
DeepSeek V2 Lite Chat
DeepSeek · duyntnet
Params15.7B
Context160K
Q4_K_M10.4 GB
GGUF
DE
deepseek-coder-6.7b-instruct
DeepSeek · duyntnet
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
MI
OpenMath-Mistral-7B-v0.1-hf
Mistral · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · duyntnet
Params1.54B
Context32K
Q4_K_M1.0 GB
Coding
YI
Nous-Hermes-2-Yi-34B
Yi · duyntnet
Params34.4B
Context4K
Q4_K_M20.7 GB
Tool use
QW
QwQ 32B
Qwen · duyntnet
Params32.8B
Context40K
Q4_K_M19.9 GB
ReasoningTool use
DU
DuckDB-NSQL-7B-v0.1
Duckdb · duyntnet
Params6.74B
Context16K
Q4_K_M4.1 GB
GGUF
LL
Meta-Llama-3-8B-Instruct
Llama · duyntnet
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
MI
SlimHercules-4.0-Mistral-7B-v0.2
Mistral · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ZE
zephyr-7b-sft-full-SPIN-iter3
Zephyr · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen2.5 14B Instruct 1M
Qwen · duyntnet
Params14.8B
Context986K
Q4_K_M9.0 GB
GGUF
LL
Llama 3.1 Nemotron Nano 8B v1
Llama · duyntnet
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
QW
Qwen3 0.6B
Qwen · duyntnet
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
DE
Deepthink Reasoning 7B imatrix
Deepthink · duyntnet
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningTool use

About duyntnet on Hugging Face

duyntnet has published 305 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Mistral. The most downloaded are Phi 3 mini 128k instruct imatrix, Aya Expanse 8b and Granite 8b Code Instruct.

The quants duyntnet publishes most often are Q8_0 (305), Q6_K (305), Q5_K_S (305) and Q5_K_M (305). Their Q4_K_M files range from 0.1 to 21.5 GB. Parameter counts run from 163M to 35B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has duyntnet published?

305 models are listed here, mainly from the Qwen, Llama and Mistral families. The most downloaded is Phi 3 mini 128k instruct imatrix.

Which quants does duyntnet publish?

The most common are Q8_0 (305 models), Q6_K (305 models), Q5_K_S (305 models) and Q5_K_M (305 models).

Keep browsing