GGUF models by tsunemoto

37 GGUF models quantized by tsunemoto on Hugging Face. Sizes run from 462M to 69B parameters. The longest trained context is 32K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
MiniChat 1.5 3B
Minichat · tsunemoto
Params3.02B
Context4K
Q4_K_M1.8 GB
GGUF
MI
Mistral 7B Instruct v0.2
Mistral · tsunemoto
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
TI
TinyDolphin 2.8 1.1b
Tinydolphin · tsunemoto
Params1.1B
Context4K
Q4_K_M0.7 GB
GGUF
LI
LiteLlama 460M 1T
Litellama · tsunemoto
Params462M
Context1K
Q4_K_M0.3 GB
GGUF
HE
Heimer kto TinyLlama 1.1B
Heimer · tsunemoto
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
TI
TinyLlama 1.1B Chat v0.6 x8 MoE
Tinyllama · tsunemoto
Params6.43B
Context2K
Q4_K_M3.6 GB
GGUF
WI
WizardMath 7B V1.1
Wizardmath · tsunemoto
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
WS
WSB GPT 7B
Wsb · tsunemoto
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
YI
Yi 1.5 34B Chat
Yi · tsunemoto
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
ME
Metis 0.3
Metis · tsunemoto
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
CO
cosmo 1b
Cosmo · tsunemoto
Params1.74B
Context2K
Q4_K_M1.1 GB
GGUF
NO
Norobara ZLoss 8x7B
Norobara · tsunemoto
Params46.7B
Context32K
Q4_K_M26.3 GB
GGUF
OP
OpenHermes Emojitron 001
Openhermes · tsunemoto
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
HE
Heimer dpo TinyLlama 1.1B
Heimer · tsunemoto
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
MI
dolphin 2.5 mixtral 8x7b
Mistral · tsunemoto
Params46.7B
Context32K
Q4_K_M26.3 GB
GGUF
MI
mistral ft optimized 1218
Mistral · tsunemoto
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
ToxicHermes 2.5 Mistral 7B
Mistral · tsunemoto
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
HE
Heimer ipo TinyLlama 1.1B
Heimer · tsunemoto
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
FL
FlatDolphinMaid 8x7B
Flatdolphinmaid · tsunemoto
Params46.7B
Context32K
Q4_K_M26.3 GB
GGUF
SE
Seraph 7B
Seraph · tsunemoto
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
LLaMAntino 2 chat 13b hf ITA
Llama · tsunemoto
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
YI
Nous Hermes 2 Yi 34B
Yi · tsunemoto
Params34.4B
Context4K
Q4_K_M20.7 GB
Tool use
GE
GEITje 7B chat
Geitje · tsunemoto
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
OP
openchat 3.5 1210
Openchat · tsunemoto
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
BU
Bucharest 0.2
Bucharest · tsunemoto
Params10.7B
Context6K
Q4_K_M6.5 GB
GGUF
MA
Magicoder S CL 7B
Magicoder · tsunemoto
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
YI
Yi 1.5 9B Chat
Yi · tsunemoto
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
SO
SOLAR 10.7B Instruct v1.0
Solar · tsunemoto
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
DO
dopeyshearedplats 1.3b v1
Dopeyshearedplats · tsunemoto
Params1.35B
Context4K
Q4_K_M0.9 GB
GGUF
BA
bagel dpo 7b v0.4
Bagel · tsunemoto
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

About tsunemoto on Hugging Face

tsunemoto has published 37 GGUF models that ggufmodels.com tracks, across families such as Yi, Mistral and Heimer. The most downloaded are MiniChat 1.5 3B, Mistral 7B Instruct v0.2 and TinyDolphin 2.8 1.1b.

The quants tsunemoto publishes most often are Q5_K_M (37), Q4_K_M (37), Q5_K_S (36) and Q4_K_S (36). Their Q4_K_M files range from 0.3 to 41.4 GB. Parameter counts run from 462M to 69B, and the longest trained context window is 32K tokens.

Frequently asked questions

What GGUF models has tsunemoto published?

37 models are listed here, mainly from the Yi, Mistral and Heimer families. The most downloaded is MiniChat 1.5 3B.

Which quants does tsunemoto publish?

The most common are Q5_K_M (37 models), Q4_K_M (37 models), Q5_K_S (36 models) and Q4_K_S (36 models).

Keep browsing