GGUF models by keisuke-miyako

302 GGUF models quantized by keisuke-miyako on Hugging Face. Sizes run from 23M to 14.7B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama 3.2 3B Instruct gguf q4 k m
Llama · keisuke-miyako
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
DE
Deepset Mxbai Embed De Large v1
Deepset · keisuke-miyako
Params486M
Context512
Q4_K_M0.3 GB
Embedding
TI
Tiny Aya Earth
Tiny · keisuke-miyako
Params3.35B
Context488K
Smallest3.6 GB
GGUF
GE
gemma 3n E4B it gguf q4 k m
Gemma · keisuke-miyako
Params6.87B
Context32K
Q4_K_M4.2 GB
GGUF
QW
Qwen3 4B Instruct 2507 gguf q4 k m
Qwen · keisuke-miyako
Params4.02B
Context256K
Q4_K_M2.5 GB
Tool use
TI
Tiny Aya Global
Tiny · keisuke-miyako
Params3.35B
Context488K
Smallest3.6 GB
GGUF
NE
NVIDIA Nemotron Nano 9B v2 Japanese gguf q4 k m
Nemotron · keisuke-miyako
Params8.89B
Context1024K
Q4_K_M6.5 GB
ReasoningTool use
QW
Qwen3 Embedding 0.6B gguf q8 0
Qwen · keisuke-miyako
Params596M
Context32K
Smallest0.6 GB
EmbeddingReasoningTool use
GE
springsea 0.2
Gemma · keisuke-miyako
Params4.65B
Context128K
Q4_K_M3.4 GB
CodingReasoningTool use
BG
bge m3 doc r2.1
BGE · keisuke-miyako
Params567M
Context8K
Smallest0.6 GB
Embedding
LL
Gemma 2 Llama Swallow 2b it v0.1 gguf q4 k m
Llama · keisuke-miyako
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
DE
DeepSeek R1 Distill Qwen2.5 1.5B gguf q4 k m
DeepSeek · keisuke-miyako
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
ET
Ettin Encoder 17m
Ettin · keisuke-miyako
Params149M
Context8K
Smallest0.0 GB
Coding
RU
ruri v3 30m gguf q8 0
Ruri · keisuke-miyako
Params37M
Context8K
Smallest0.0 GB
GGUF
LU
Lucie 7B Instruct v1.1 gguf q4 k m
Lucie · keisuke-miyako
Params6.71B
Context31K
Q4_K_M4.1 GB
GGUF
HA
harrier oss v1 0.6b gguf f16
Harrier · keisuke-miyako
Params596M
Context32K
Smallest1.2 GB
ReasoningTool use
XL
xLAM 2 1b Fc R
Xlam · keisuke-miyako
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
HA
Harrier Oss v1 270m
Harrier · keisuke-miyako
Params268M
Context32K
Smallest0.3 GB
GGUF
EU
EuroLLM 1.7B Instruct gguf q4 k m
Eurollm · keisuke-miyako
Params1.66B
Context4K
Q4_K_M1.0 GB
GGUF
GE
gemma 3 1b it gguf q4 k m
Gemma · keisuke-miyako
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
BG
bge m3 lemur r3
BGE · keisuke-miyako
Params567M
Context8K
Smallest0.6 GB
Embedding
LF
doc4d 2026 08 05
Lfm · keisuke-miyako
Params354M
Context125K
Smallest0.4 GB
EmbeddingTool use
EU
EuroLLM 9B Instruct 2512
Eurollm · keisuke-miyako
Params9.15B
Context32K
Q4_K_M5.6 GB
GGUF
FU
functiongemma 270m it gguf q4 k m
Functiongemma · keisuke-miyako
Params268M
Context32K
Q4_K_M0.3 GB
Tool use
QW
Qwen3.5-0.8B
Qwen · keisuke-miyako
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool use
MM
mmarco mMiniLMv2 L12 H384 v1 gguf q4 k m
Mmarco · keisuke-miyako
Params118M
Context512
Q4_K_M0.1 GB
GGUF
GT
Gte Reranker Modernbert Base
Gte · keisuke-miyako
Params150M
Context8K
Q4_K_M0.1 GB
Embedding
IT
ModernBERT Base
Italian · keisuke-miyako
Params135M
Context8K
Smallest0.1 GB
GGUF
LF
LFM2.5 1.2B Instruct gguf q4 k m
Lfm · keisuke-miyako
Params1.17B
Context125K
Q4_K_M0.7 GB
Tool use
RA
RakutenAI 2.0 Mini Instruct
Rakutenai · keisuke-miyako
Params1.53B
Context128K
Smallest1.6 GB
GGUF

Keep browsing