GGUF models by Aashraf995

37 GGUF models quantized by Aashraf995 on Hugging Face. Sizes run from 494M to 14.8B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
KA
KaLM Embedding Multilingual Mini Instruct v2.5
Kalm · Aashraf995
Params494M
Context128K
Smallest0.5 GB
Embedding
QW
CodeQwen1.5 7B Chat
Qwen · Aashraf995
Params7.25B
Context64K
Q4_K_M4.7 GB
GGUF
CO
Codegemma 7b
Codegemma · Aashraf995
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
QW
Homer-v1.0-Qwen2.5-7B
Qwen · Aashraf995
Params7.62B
Context128K
Smallest6.3 GB
Tool use
QW
Qwen3 Embedding 0.6B
Qwen · Aashraf995
Params596M
Context32K
Smallest0.6 GB
EmbeddingReasoningTool use
LL
Llama 3.1 MedIT SUN 8B Q4 K M
Llama · Aashraf995
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
OP
OpenCoder 8B Instruct Abliterated
Opencoder · Aashraf995
Params7.77B
Context8K
Q4_K_M4.7 GB
Coding
VI
VibeThinker 1.5B
Vibethinker · Aashraf995
Params1.78B
Context128K
Smallest1.9 GB
Coding
ME
Mem Agent
Mem · Aashraf995
Params4.02B
Context256K
Q4_K_M2.5 GB
GGUF
CY
cybertron v4 qw7B UNAMGS Q8 0
Cybertron · Aashraf995
Params7.62B
Context128K
Smallest8.1 GB
Tool use
QW
Homer-v1.0-Qwen2.5-7B
Qwen · Aashraf995
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
NX
Nxcode CQ 7B Orpo
Nxcode · Aashraf995
Params7.25B
Context64K
Q4_K_M4.7 GB
Coding
VI
VibeThinker 1.5B
Vibethinker · Aashraf995
Params1.78B
Context128K
Q4_K_M1.1 GB
Coding
DE
Delirium v1 Q6 K
Delirium · Aashraf995
Params9.24B
Context8K
Smallest7.6 GB
GGUF
CH
Chocolatine 3B Instruct DPO Revised Q8 0
Chocolatine · Aashraf995
Params3.82B
Context4K
Smallest4.1 GB
GGUF
NE
NVIDIA Nemotron Nano 9B v2
Nemotron · Aashraf995
Params8.89B
Context1024K
Q4_K_M6.5 GB
ReasoningTool use
CU
CursorCore QW2.5 7B Q4 K M
Cursorcore · Aashraf995
Params7.61B
Context32K
Q4_K_M4.7 GB
Coding
DE
DeepMagiCoder 6.7B DS Base Q4 K M
Deepmagicoder · Aashraf995
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
Qwen2 NextGen 8b Q4 K M
Qwen · Aashraf995
Params8.54B
Context32K
Q4_K_M5.2 GB
GGUF
QW
Homer v0.5 Qwen2.5 7B
Qwen · Aashraf995
Params7.62B
Context32K
Smallest8.1 GB
Tool use
SA
SauerkrautLM v2 14b DPO
Sauerkrautlm · Aashraf995
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
IN
internlm2 5 7b chat Q8 0
InternLM · Aashraf995
Params7.74B
Context32K
Smallest8.2 GB
GGUF
GE
recoilme gemma 2 9B v0.3 Q5 K S
Gemma · Aashraf995
Params9.24B
Context8K
Smallest6.5 GB
GGUF
M1
m 1 Q4 K M
Aashraf995
Params7.61B
Context32K
Q4_K_M4.7 GB
Tool use
CY
cybertron v4 qw7B MGS Q8 0
Cybertron · Aashraf995
Params7.62B
Context128K
Smallest8.1 GB
Tool use
CR
Creative nerd0.1 Q4 K M
Creative · Aashraf995
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
MA
Marco o1 Q8 0
Marco · Aashraf995
Params7.62B
Context32K
Smallest8.1 GB
GGUF
NX
Nxcode CQ 7B Orpo
Nxcode · Aashraf995
Params7.25B
Context64K
Smallest7.7 GB
Coding
PH
Phi 3 Mini 128k Instruct
Phi · Aashraf995
Params3.82B
Context128K
Smallest4.1 GB
Coding
GE
Gemma 2 9b It
Gemma · Aashraf995
Params9.24B
Context8K
Smallest7.6 GB
GGUF

About Aashraf995 on Hugging Face

Aashraf995 has published 37 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Opencoder. The most downloaded are KaLM Embedding Multilingual Mini Instruct v2.5, CodeQwen1.5 7B Chat and Codegemma 7b.

The quants Aashraf995 publishes most often are Q4_K_M (16), Q8_0 (15), Q6_K (4) and Q5_K_S (1). Their Q4_K_M files range from 1.1 to 9.0 GB. Parameter counts run from 494M to 14.8B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has Aashraf995 published?

37 models are listed here, mainly from the Qwen, Gemma and Opencoder families. The most downloaded is KaLM Embedding Multilingual Mini Instruct v2.5.

Which quants does Aashraf995 publish?

The most common are Q4_K_M (16 models), Q8_0 (15 models), Q6_K (4 models) and Q5_K_S (1 models).

Keep browsing