GGUF models by ysn-rfd

149 GGUF models quantized by ysn-rfd on Hugging Face. Sizes run from 7M to 40.2B parameters. The longest trained context is 501K tokens.

Most downloadedNewestLargestLongest contextSmallest
CH
Chatbench Distilgpt2
Chatbench · ysn-rfd
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
TE
Test_FIBO_IDEN_FFN
Test · ysn-rfd
Params6.87B
Context32K
Smallest4.9 GB
GGUF
AR
Arch Function Chat 3B
Arch · ysn-rfd
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
CH
OpenELM 3B Instruct
Chatbench · ysn-rfd
Params3.04B
Context1K
Smallest0.2 GB
GGUF
LL
calme-3.3-llamaloi-3b
Llama · ysn-rfd
Params3.21B
Context128K
Smallest1.9 GB
Tool use
ST
Starcoder2 3b
StarCoder · ysn-rfd
Params3.03B
Context16K
Q4_K_M1.9 GB
Coding
RE
Refact 1_6B Fim
Refact · ysn-rfd
Params1.59B
Context4K
Q4_K_M1.0 GB
Coding
GE
Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking
Gemma · ysn-rfd
Params40.2B
Context128K
Smallest42.7 GB
CodingReasoningRoleplay
HE
NSFW 3B Q2 K
Helvete · ysn-rfd
Params2.8B
Context4K
Smallest1.1 GB
GGUF
TI
TinySwallow 1.5B Instruct
Tinyswallow · ysn-rfd
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
LL
CodeLlama 7b Python Hf
Llama · ysn-rfd
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
Dolphin3.0 Qwen2.5 3B
Qwen · ysn-rfd
Params3.09B
Context32K
Smallest1.8 GB
CodingTool use
OP
OpenCoder 1.5B Instruct
Opencoder · ysn-rfd
Params1.91B
Context4K
Smallest1.2 GB
Coding
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · ysn-rfd
Params7.62B
Context128K
Smallest4.4 GB
ReasoningTool use
QW
Qwen2.5 1.5B Instruct
Qwen · ysn-rfd
Params1.54B
Context32K
Smallest1.6 GB
Tool use
AC
AceInstruct 1.5B
Aceinstruct · ysn-rfd
Params1.78B
Context128K
Smallest1.1 GB
Coding
MI
Ministral 3b instruct
Mistral · ysn-rfd
Params3.32B
Context128K
Q4_K_M2.0 GB
GGUF
FI
FIBO_IDEN_MODEL
Fibo · ysn-rfd
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
LL
LLuMi_Think_3B
Llumi · ysn-rfd
Params3.09B
Context32K
Smallest1.8 GB
ReasoningTool use
PE
PersianMind v1.0
Persianmind · ysn-rfd
Params6.82B
Context2K
Smallest4.7 GB
GGUF
LL
Dolphin 3.0 Llama 3.2 3B
Llama · ysn-rfd
Params3.21B
Context128K
Smallest1.9 GB
CodingTool use
HA
HallOumi 8B
Halloumi · ysn-rfd
Params8.03B
Context128K
Smallest4.7 GB
Tool use
HU
Huihui MoE 12B A4B Abliterated
Huihui · ysn-rfd
Params12.5B
Context40K
Q4_K_M7.6 GB
GGUF
BA
BabyMistral
Babymistral · ysn-rfd
Params1.55B
Context8K
Smallest0.9 GB
GGUF
QW
Dolphin3.0 Qwen2.5 1.5B
Qwen · ysn-rfd
Params1.54B
Context128K
Smallest0.9 GB
CodingTool use
HE
HelpingAI2.5 2B
Helpingai · ysn-rfd
Params1.71B
Context8K
Smallest1.0 GB
GGUF
HE
HelpingAI2.5 5B
Helpingai · ysn-rfd
Params5.13B
Context128K
Smallest3.0 GB
Tool use
OP
Openhands Lm 7b v0.1
Openhands · ysn-rfd
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
LL
Chatbench Llama3 8b
Llama · ysn-rfd
Params7M
Context8K
Smallest0.0 GB
GGUF
LL
DeepHermes 3 Llama 3 3B Preview
Llama · ysn-rfd
Params3.21B
Context128K
Smallest1.9 GB
ReasoningRoleplayTool use

About ysn-rfd on Hugging Face

ysn-rfd has published 149 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Gpt. The most downloaded are Chatbench Distilgpt2, Test_FIBO_IDEN_FFN and Arch Function Chat 3B.

The quants ysn-rfd publishes most often are Q8_0 (101), Q4_0 (58), Q5_0 (53) and Q4_K_M (24). Their Q4_K_M files range from 0.1 to 7.6 GB. Parameter counts run from 7M to 40.2B, and the longest trained context window is 501K tokens.

Frequently asked questions

What GGUF models has ysn-rfd published?

149 models are listed here, mainly from the Qwen, Llama and Gpt families. The most downloaded is Chatbench Distilgpt2.

Which quants does ysn-rfd publish?

The most common are Q8_0 (101 models), Q4_0 (58 models), Q5_0 (53 models) and Q4_K_M (24 models).

Keep browsing