GGUF models by tatsuyaaaaaaa

76 GGUF models quantized by tatsuyaaaaaaa on Hugging Face. Sizes run from 268M to 34.7B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
TR
Translategemma 4b It
Translategemma · tatsuyaaaaaaa
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
TR
Translategemma 12b It
Translategemma · tatsuyaaaaaaa
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
NE
NVIDIA Nemotron Nano 9B v2
Nemotron · tatsuyaaaaaaa
Params8.89B
Context1024K
Q4_K_M6.5 GB
ReasoningTool use
QW
Qwen3.5 4B
Qwen · tatsuyaaaaaaa
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
QW
Qwen3 Swallow 8B RL v0.2
Qwen · tatsuyaaaaaaa
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen3.5 0.8B
Qwen · tatsuyaaaaaaa
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool use
QW
Qwen2.5 VL 3B Instruct
Qwen · tatsuyaaaaaaa
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
QW
Qwen3.5 35B A3B
Qwen · tatsuyaaaaaaa
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
NE
NVIDIA Nemotron Nano 9B v2 Japanese
Nemotron · tatsuyaaaaaaa
Params8.89B
Context1024K
Q4_K_M6.5 GB
ReasoningTool use
QW
Qwen3 Coder 30B A3B Instruct
Qwen · tatsuyaaaaaaa
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
LF
LFM2 VL 3B
Lfm · tatsuyaaaaaaa
Params2.57B
Context125K
Q4_K_M1.6 GB
Vision
MU
multilingual e5 base
Multilingual · tatsuyaaaaaaa
Params277M
Context512
Q4_K_M0.2 GB
GGUF
LF
LFM2 VL 450M
Lfm · tatsuyaaaaaaa
Params354M
Context125K
Q4_K_M0.2 GB
Vision
QW
Flux Japanese Qwen2.5 32B Instruct V1.0
Qwen · tatsuyaaaaaaa
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
GE
Gemma 3 1b It
Gemma · tatsuyaaaaaaa
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
QW
Qwen3 VL 8B Instruct
Qwen · tatsuyaaaaaaa
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
SH
shisa v2.1 unphi4 14b
Shisa · tatsuyaaaaaaa
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
LL
Llama 3 ELYZA JP 8B
Llama · tatsuyaaaaaaa
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Gemma 3 270m It
Gemma · tatsuyaaaaaaa
Params268M
Context32K
Q4_K_M0.3 GB
GGUF
QW
Qwen3.5 27B
Qwen · tatsuyaaaaaaa
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
PH
Phi 4 Mini Reasoning
Phi · tatsuyaaaaaaa
Params3.84B
Context128K
Q4_K_M2.5 GB
ReasoningTool use
GP
Gpt Oss 20b
gpt-oss · tatsuyaaaaaaa
Params20.9B
Context128K
Smallest12.1 GB
Tool use
QW
Qwen3.5 2B
Qwen · tatsuyaaaaaaa
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool use
QW
Qwen3.5 9B
Qwen · tatsuyaaaaaaa
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
GP
GPT OSS Swallow 20B SFT v0.1
gpt-oss · tatsuyaaaaaaa
Params20.9B
Context128K
Smallest12.1 GB
Tool use
QW
Qwen3 30B A3B Instruct 2507
Qwen · tatsuyaaaaaaa
Params30.5B
Context256K
Q4_K_M18.6 GB
Tool use
TI
TinySwallow 1.5B Instruct
Tinyswallow · tatsuyaaaaaaa
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
LF
LFM2.5 1.2B JP
Lfm · tatsuyaaaaaaa
Params1.17B
Context125K
Q4_K_M0.7 GB
Tool use
QW
Qwen3 VL 4B Instruct
Qwen · tatsuyaaaaaaa
Params4.02B
Context256K
Q4_K_M2.5 GB
Tool useVision
LF
LFM2 VL 1.6B
Lfm · tatsuyaaaaaaa
Params1.17B
Context125K
Smallest0.5 GB
Vision

About tatsuyaaaaaaa on Hugging Face

tatsuyaaaaaaa has published 76 GGUF models that ggufmodels.com tracks, across families such as Qwen, Lfm and Gemma. The most downloaded are Translategemma 4b It, Translategemma 12b It and NVIDIA Nemotron Nano 9B v2.

The quants tatsuyaaaaaaa publishes most often are Q8_0 (75), Q6_K (70), Q5_K_S (70) and Q5_K_M (70). Their Q4_K_M files range from 0.2 to 21.2 GB. Parameter counts run from 268M to 34.7B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has tatsuyaaaaaaa published?

76 models are listed here, mainly from the Qwen, Lfm and Gemma families. The most downloaded is Translategemma 4b It.

Which quants does tatsuyaaaaaaa publish?

The most common are Q8_0 (75 models), Q6_K (70 models), Q5_K_S (70 models) and Q5_K_M (70 models).

Keep browsing