Small GGUF models
91171 GGUF models with roughly 4B to 9B parameters. Sizes run from 3.51B to 9.5B parameters. The longest trained context is 4194304K tokens.
SP
Spark X2.5 4B Heretic jp
Spark · soyaakinohara
Params4.1B
Context1024K
Q4_K_M2.6 GB
QW
Bonsai-27B-dspark
Qwen · prism-ml
Params3.6B
Context4K
Smallest1.8 GB
GR
Granite 4.2 3b
Granite · ibm-granite
Params3.66B
Context128K
Q4_K_M2.2 GB
GR
Granite 4.2 8b
Granite · ibm-granite
Params8.79B
Context128K
Q4_K_M5.3 GB
QW
Qwen2.5-Vl-7B-Instruct
Qwen · unsloth
Params7.62B
Context125K
Q4_K_M4.7 GB
LI
Ling 3.0 Tiny
Ling · bloomer010
Params7.89B
Context128K
Q4_K_M4.8 GB
SP
spark s1 4b v6
Spark · abhishek085
Params4.21B
Context256K
Smallest3.5 GB
QW
Qwen2.5 7B Instruct
Qwen · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
QW
Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16
Qwen · HauhauCS
Params4.21B
Context256K
Q4_K_M2.7 GB
XX
T5 V1_1 Xxl
Xxl · city96
Params4.76B
Context512
Q4_K_M2.9 GB
QW
Parable Qwen3 8B Claude Fable 5
Qwen · AnkitAI
Params8.2B
Context40K
Q4_K_M5.0 GB
QW
Parable Qwen3 4B Claude Fable 5
Qwen · AnkitAI
Params4B
Context40K
Q4_K_M2.5 GB
CA
Carbon 8B
Carbon · HuggingFaceBio
Params8.26B
Context32K
Q4_K_M5.5 GB
QW
Huihui Qwen3.5 9B Abliterated
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
Qwen3-Vl-8B-Instruct
Qwen · unsloth
Params8.19B
Context256K
Q4_K_M5.0 GB
AG
Agents A1 4B
Agents · InternScience
Params4.21B
Context256K
Smallest4.5 GB
QW
Qwen Image 2.1 Turbo
Qwen · AtomicChat
Params7.12B
Context—
Smallest2.6 GB
YU
Yue2-3B-GGUF
Yue · audio-cpp
Params3.63B
Context—
Smallest0.3 GB
EX
Experiment26 7B passthrough 10slice
Experiment · babybirdprd
Params7B
Context—
Q4_K_M0.0 GB
QW
Qwen3.5 9B
Qwen · bartowski
Params9.2B
Context256K
Q4_K_M6.2 GB
AR
ark asr 3b
Ark · cstr
Params3.75B
Context—
Smallest0.0 GB
SP
Spark X2.6 4B
Spark · XHToken
Params4.45B
Context1024K
Q4_K_M3.5 GB
AG
Agents A1 4B
Agents · InternScience
Params4.21B
Context256K
Q4_K_M2.7 GB
GE
gemma 4 E2B it qat q4 0
Gemma · google
Params4.63B
Context128K
Smallest3.3 GB
GR
Parable Granite 4.1 8B Claude Fable 5
Granite · AnkitAI
Params8.38B
Context128K
Q4_K_M5.1 GB
GE
gemma-4-E2B-it
Gemma · ggml-org
Params4.65B
Context128K
Smallest0.1 GB
QW
Qwen_Qwen3.5 4B
Qwen · lmstudio-community
Params4.21B
Context256K
Q4_K_M2.7 GB
HO
Diplodocus preview 4
Horizon · OsaurusAI
Params9B
Context512K
Q4_K_M6.3 GB
DE
Deepseek-R1-0528-Qwen3-8B
DeepSeek · unsloth
Params8.19B
Context128K
Q4_K_M5.0 GB
IM
Z Image
Image · unsloth
Params6.15B
Context—
Q4_K_M3.9 GB