GGUF models by aashish1904

39 GGUF models quantized by aashish1904 on Hugging Face. Sizes run from 752M to 32.5B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen Qwen3.5 2B Base
Qwen · aashish1904
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool use
LL
Meta Llama Llama 3.2 3B Instruct
Llama · aashish1904
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
DA
Alibaba Apsara DASD 4B Thinking
Dasd · aashish1904
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen Qwen3 8B
Qwen · aashish1904
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen Qwen3 1.7B
Qwen · aashish1904
Params2.03B
Context40K
Q4_K_M1.3 GB
ReasoningTool use
QW
Qwen Qwen3.5 0.8B
Qwen · aashish1904
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool use
JA
Janhq Jan v3 4B Base Instruct
Jan · aashish1904
Params4.41B
Context256K
Q4_K_M2.7 GB
Tool use
QW
MagicalAlchemist Qwen3 1.7B Magic_decensored
Qwen · aashish1904
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
LL
Llama 3.2 1B Instruct
Llama · aashish1904
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
QW
Qwen Qwen3.5 2B
Qwen · aashish1904
Params1.88B
Context256K
Smallest0.9 GB
ReasoningTool use
LL
Llama 3.2 3B
Llama · aashish1904
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
MI
Codestral 22B v0.1
Mistral · aashish1904
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
MI
Ministral 8B Instruct 2410 HF
Mistral · aashish1904
Params8.02B
Context32K
Q4_K_M4.9 GB
Tool use
NE
Nvidia Nemotron 3.5 Content Safety
Nemotron · aashish1904
Params3.88B
Context128K
Q4_K_M2.5 GB
Reasoning
QW
Qwen Qwen2.5 7B Instruct
Qwen · aashish1904
Params7.62B
Context32K
Smallest3.0 GB
Tool use
GE
Gemma 2 27b It Abliterated
Gemma · aashish1904
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
LL
Llama 3.1 Swallow 8B v0.1 Q4 K M
Llama · aashish1904
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GR
Granite 3.0 2b Instruct
Granite · aashish1904
Params2.63B
Context4K
Smallest2.8 GB
Tool use
LL
reflection llama 3.1 8B Solshine trainround3 16bit Q4 K M
Llama · aashish1904
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
MI
Mistral Small Instruct 2409
Mistral · aashish1904
Params22.2B
Context128K
Smallest8.3 GB
Tool use
GR
Granite 3.0 8b Instruct
Granite · aashish1904
Params8.17B
Context4K
Q4_K_M4.9 GB
Tool use
DA
datagemma rag 27b it Q2 K
Datagemma · aashish1904
Params27.2B
Context8K
Smallest10.4 GB
GGUF
TH
Theia 21B v2 Q4 K M
Theia · aashish1904
Params20.4B
Context1000K
Q4_K_M12.4 GB
GGUF
MI
mistral rrc Q4 K M
Mistral · aashish1904
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GR
Granite 3.0 8b Instruct
Granite · aashish1904
Params8.17B
Context4K
Smallest8.7 GB
Tool use
GR
Granite 3.0 8b Instruct
Granite · aashish1904
Params8.17B
Context4K
Smallest3.1 GB
Tool use
LL
gpt5o reflexion q agi llama 3.1 8b Q4 K M
Llama · aashish1904
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
DA
datagemma rag 27b it Q4 K M
Datagemma · aashish1904
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
MI
Ministral 8B Instruct 2410 HF
Mistral · aashish1904
Params8.02B
Context32K
Smallest3.2 GB
Tool use
GR
Granite 3.0 2b Instruct
Granite · aashish1904
Params2.63B
Context4K
Q4_K_M1.6 GB
Tool use

About aashish1904 on Hugging Face

aashish1904 has published 39 GGUF models that ggufmodels.com tracks, across families such as Qwen, Mistral and Llama. The most downloaded are Qwen Qwen3.5 2B Base, Meta Llama Llama 3.2 3B Instruct and Alibaba Apsara DASD 4B Thinking.

The quants aashish1904 publishes most often are Q4_K_M (25), Q2_K (18), Q8_0 (12) and Q3_K_S (10). Their Q4_K_M files range from 0.5 to 19.6 GB. Parameter counts run from 752M to 32.5B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has aashish1904 published?

39 models are listed here, mainly from the Qwen, Mistral and Llama families. The most downloaded is Qwen Qwen3.5 2B Base.

Which quants does aashish1904 publish?

The most common are Q4_K_M (25 models), Q2_K (18 models), Q8_0 (12 models) and Q3_K_S (10 models).

Keep browsing