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
BG
bge m3 lemur r2
BGE · keisuke-miyako
Params567M
Context8K
Smallest0.6 GB
Embedding
RE
reader lm 1.5b gguf q8 0
Reader · keisuke-miyako
Params1.54B
Context250K
Smallest1.6 GB
GGUF
LL
Gemma 2 Llama Swallow 9b it v0.1 gguf q4 k m
Llama · keisuke-miyako
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
LL
Llama 3.1 Swallow 8B Instruct v0.5 gguf q4 k m
Llama · keisuke-miyako
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
HA
Hammer2.1 3b gguf q4 k m
Hammer · keisuke-miyako
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
MI
Ministral 3 3B Instruct 2512 gguf q4 k m
Mistral · keisuke-miyako
Params3.43B
Context256K
Q4_K_M2.1 GB
Tool useVision
EM
embeddinggemma 300m gguf q8 0
Embeddinggemma · keisuke-miyako
Params303M
Context2K
Smallest0.3 GB
Embedding
FA
Falcon H1 1.5B Instruct gguf q4 k m
Falcon · keisuke-miyako
Params1.55B
Context128K
Q4_K_M0.9 GB
Tool use
MU
multilingual e5 base gguf f16
Multilingual · keisuke-miyako
Params277M
Context512
Smallest0.6 GB
GGUF
QW
Qwen3 Embedding 4B gguf q4 k m
Qwen · keisuke-miyako
Params4.02B
Context40K
Q4_K_M2.5 GB
EmbeddingTool use
MX
Mxbai Embed Large v1
Mxbai · keisuke-miyako
Params334M
Context512
Smallest0.4 GB
Embedding
FA
Falcon3 1B Instruct gguf q4 k m
Falcon · keisuke-miyako
Params1.67B
Context8K
Q4_K_M1.1 GB
Tool use
LA
e5 large v2 gguf q4 k m
Large · keisuke-miyako
Params334M
Context512
Q4_K_M0.2 GB
GGUF
LL
Gemma 2 Llama Swallow 9b pt v0.1 gguf q4 k m
Llama · keisuke-miyako
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
QW
Qwen3 1.7B gguf q8 0
Qwen · keisuke-miyako
Params2.03B
Context40K
Smallest2.2 GB
ReasoningTool use
MO
Modernbert Ja 70m
Modernbert · keisuke-miyako
Params70M
Context8K
Smallest0.1 GB
GGUF
RA
RakutenAI 7B Instruct
Rakutenai · keisuke-miyako
Params7.37B
Context32K
Q4_K_M4.5 GB
GGUF
EU
EuroLLM 9B Instruct gguf q4 k m
Eurollm · keisuke-miyako
Params9.15B
Context4K
Q4_K_M5.6 GB
GGUF
QW
Qwen2.5 7B Instruct gguf q4 k m
Qwen · keisuke-miyako
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
MM
mmarco mMiniLMv2 L12 H384 v1 gguf q8 0
Mmarco · keisuke-miyako
Params118M
Context512
Smallest0.1 GB
Coding
BG
bge m3 legal euro r26
BGE · keisuke-miyako
Params567M
Context8K
Smallest0.6 GB
Embedding
BG
bge m3 doc r4
BGE · keisuke-miyako
Params567M
Context8K
Smallest0.6 GB
Embedding
PH
Phi 4 gguf q4 k m
Phi · keisuke-miyako
Params14.7B
Context16K
Q4_K_M9.1 GB
Reasoning
FA
Falcon H1 0.5B Instruct gguf q8 0
Falcon · keisuke-miyako
Params521M
Context16K
Smallest0.6 GB
Tool use
BG
bge reranker v2 m3 gguf q8 0
BGE · keisuke-miyako
Params568M
Context8K
Smallest0.6 GB
Embedding
QW
Qwen3 Reranker 4B gguf q8 0
Qwen · keisuke-miyako
Params4.02B
Context40K
Smallest4.3 GB
EmbeddingReasoningTool use
LA
LaBSE gguf q4 k m
Labse · keisuke-miyako
Params470M
Context512
Q4_K_M0.4 GB
GGUF
LL
Llama 3.1 8B Instruct gguf q4 k m
Llama · keisuke-miyako
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Llama 3.2 1B Instruct gguf q4 k m
Llama · keisuke-miyako
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
JI
jina reranker v1 turbo en gguf q8 0
Jina · keisuke-miyako
Params38M
Context8K
Smallest0.0 GB
Embedding

Keep browsing