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.

Most downloadedNewestLargestLongest contextSmallest
MI
MiMo 7B RL
Mimo · jedisct1
Params7.6B
Context32K
Q4_K_M4.7 GB
Reasoning
GL
Gliese OCR 7B Post2.0 Final
Gliese · prithivMLmods
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
MI
rossascends_mistral_7b_dolphin2.1_lima0.5_fp16
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP
Qwen · CapitalSTEEZ47
Params8.95B
Context256K
Q4_K_M6.8 GB
CodingReasoningRoleplay
MA
MAmmoTH2-8B-Plus
Mammoth · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LL
llama2 7b chat uncensored i1
Llama · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
QW
Qwen3.5 9B Qwensploit CyberSecurity
Qwen · xtools-at
Params8.95B
Context1024K
Q4_K_M5.6 GB
CodingReasoningTool use
LL
Llama3 DocChat 1.0 8B
Llama · bartowski
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
RI
Riva Translate 4B Instruct v1.1
Riva · mradermacher
Params4.18B
Context8K
Q4_K_M2.8 GB
GGUF
QW
Qwen3 8B 192k Josiefied Uncensored NEO Max
Qwen · DavidAU
Params8.19B
Context192K
Q4_K_M5.8 GB
ReasoningRoleplay
VI
Vicuna 7b v1.3
Vicuna · RichardErkhov
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
MI
Mixtral AI Cyber 5.0
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
QW
Qwen3 VL 4B Instruct Heretic
Qwen · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
Vision
MI
Ministral 3 8B Reasoning 2512 It
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningTool use
GE
Gemma 4 Rust Coder
Gemma · MassivDash
Params4.65B
Context128K
Q4_K_M3.4 GB
CodingVision
EX
models--automerger--Experiment27pasticheT3qm7xp-7B
Experiment · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
KU
KukulStanta InfinityRP 7B slerp
Kukulstanta · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AL
ALLaM 7B Instruct Preview
Allam · bartowski
Params7B
Context4K
Q4_K_M4.3 GB
GGUF
QW
Qwen3.5 9B Abliterated Claude 4.6 Opus Reasoning Distilled v2
Qwen · Abiray
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningVision
YI
Yi 1.5 9B Chat 16K Abliterated
Yi · mradermacher
Params8.83B
Context16K
Q4_K_M5.3 GB
GGUF
VI
Vistral 7B ties
Vistral · mradermacher
Params5.5B
Context32K
Q4_K_M3.5 GB
GGUF
QW
qwen3.5 4B typescript coder
Qwen · MassivDash
Params4.2B
Context256K
Q4_K_M2.7 GB
CodingVision
YI
Yi 1.5 6B Chat
Yi · RichardErkhov
Params6.06B
Context4K
Q4_K_M3.7 GB
GGUF
IN
models--automerger--NeuralsynthesisInex12-7B
Inex · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
VI
Vicuna 7b v1.3
Vicuna · RichardErkhov
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
MI
mistral 7b grok
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
HU
Huihui Qwopus3.5 9B v3 Abliterated
Huihui · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
EX
Experimentmultiverse 7B slerp
Experimentmultiverse · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
MI
Configurable-Mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GR
Ibm Granite_Granite 4.1 8b
Granite · lmstudio-community
Params8.79B
Context128K
Q4_K_M5.3 GB
GGUF

Other sizes

Keep browsing