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
LL
Hermes 3 Llama 3.1 8B Lorablated
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
Tool use
LL
Meta-Llama-3-8B-Instruct-abliterated-v3
Llama · legraphista
Params8B
Context8K
Smallest2.0 GB
GGUF
MI
kolibri-vikhr-mistral-0427
Mistral · Vikhrmodels
Params7.6B
Context32K
Q4_K_M4.6 GB
GGUF
MI
mlabonne_neuralhermes-2.5-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
TR
Trida2.0 4B
Trida · mradermacher
Params4.84B
Context256K
Q4_K_M3.1 GB
ReasoningTool use
EU
EuroLLM 9B Instruct
Eurollm · bartowski
Params9.15B
Context4K
Q4_K_M5.6 GB
GGUF
WI
ehartford_wizardlm-7b-v1.0-uncensored
Wizardlm · TheBloke
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
NE
NeoHorse 1 4B
Neohorse · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
QW
Qwen3.5 4B EmperoAI Qwen3.8 Distill
Qwen · insraq
Params4.33B
Context256K
Q4_K_M2.8 GB
GGUF
PI
piano-medley-7b
Piano · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AM
AMALIA 9B 0626 SFT
Amalia · NoxNotreve
Params9.15B
Context32K
Q4_K_M5.6 GB
GGUF
RW
rwitz_go-bruins-v2
Rwitz · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
FR
FrogNano 4B 2609
Frognano · NANI-Nithin
Params4.33B
Context256K
Q4_K_M2.8 GB
CodingVision
LL
Colossal LLaMA 2 7b Base
Llama · mradermacher
Params7.04B
Context4K
Q4_K_M4.3 GB
GGUF
MI
mathstral-7B-v0.1
Mistral · bartowski
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
AN
Anubis Mini 8B v1
Anubis · bartowski
Params8B
Context128K
Q4_K_M5.1 GB
GGUF
NO
Novel Humanize 4b
Novel · bartowski
Params4.02B
Context40K
Q4_K_M2.6 GB
ReasoningTool use
NI
Ninja-v1-NSFW-RP
Ninja · mradermacher
Params7.24B
Context4K
Q4_K_M4.4 GB
Roleplay
LL
dolphin-2.9.1-llama-3-8b
Llama · legraphista
Params8B
Context8K
Smallest2.0 GB
CodingTool use
HU
HuatuoGPT O1 7B
Huatuogpt · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Reasoning
HU
Huihui LFM2.5 8B A1B Abliterated
Huihui · mradermacher
Params8.47B
Context125K
Q4_K_M5.2 GB
GGUF
QW
Darrellbest Qwen Image 2.1 PE T2I Heretic
Qwen · darrellbest
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
LL
georgesung_llama2_7b_chat_uncensored
Llama · TheBloke
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
HU
HunyuanVideo 1.5 I2V 480p
Hunyuanvideo · jayn7
Params8.33B
Context—
Q4_K_M5.1 GB
GGUF
NE
NeuralDaredevil 8B abliterated
Neuraldaredevil · QuantFactory
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
GL
Glm-4.1V-9B-Thinking
GLM · unsloth
Params9.4B
Context64K
Q4_K_M6.2 GB
ReasoningVision
DE
DeepSeek R1 Distill Llama 8B Abliterated
DeepSeek · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
MP
Mpt 7b Storywriter
Mpt · mradermacher
Params6.65B
Context64K
Q4_K_M4.3 GB
GGUF
LL
Hermes 3 Llama 3.1 8B Lorablated
Llama · mlabonne
Params8B
Context128K
Q4_K_M4.9 GB
Tool use
CO
codegeex4-all-9b
Codegeex · legraphista
Params9.4B
Context128K
Smallest3.1 GB
GGUF

Other sizes

Keep browsing