GGUF models that fit in 8 GB

151917 GGUF language models have at least one quant whose estimated memory use is 8 GB or less at 8K context. Each card shows the largest quant that fits. Sizes run from 1M to 20260731B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
qwen3.5 4B super coder
Qwen · jica98
Params4.33B
Context256K
Best fitQ4_0 4.2 GB
CodingReasoningTool use
LL
vntl llama3 8b v2
Llama · lmg-anon
Params8B
Context8K
Best fitQ5_K_M 7.3 GB
GGUF
LL
Llama Joycaption Beta One Hf Llava
Llama · concedo
Params8B
Context128K
Best fitQ4_K 6.5 GB
Vision
MA
MN 12B Mag Mell R1
Mag · mradermacher
Params12.2B
Context1000K
Best fitQ3_K_M 7.9 GB
Reasoning
TI
TIPO 500M
Tipo · KBlueLeaf
Params508M
Context2K
Best fitF16 2.4 GB
Vision
MI
avemio digital mistral 7b Sft pretrain 6000 steps merge
Mistral · RichardErkhov
Params7.24B
Context—
Best fitQ4_0 5.1 GB
GGUF
PH
Phi 3 mini 4k instruct
Phi · microsoft
Params3.82B
Context4K
Smallest2.4 GB
Coding
SM
smollm2 360m aac watch
SmolLM · dcostenco
Params362M
Context8K
Smallest0.2 GB
GGUF
MU
multilingual e5 large instruct
Multilingual · Ralriki
Params559M
Context512
Best fitF16 2.4 GB
GGUF
OR
Ornith 1.5 35B A3B Huihui Sangreal MTP ICE
Ornith · gbuzhf
Params35.5B
Context256K
Smallest0.2 GB
ReasoningTool use
LF
LFM2.5 VL 450M
Lfm · LiquidAI
Params354M
Context125K
Best fitF32 2.5 GB
Vision
QW
Qwen3 4B RPG Roleplay V2
Qwen · Chun121
Params4B
Context32K
Best fitQ8_0 6.0 GB
Roleplay
BI
bitnet b1.58 2B 4T
Bitnet · microsoft
Params2.41B
Context4K
Smallest1.2 GB
GGUF
QW
Qwen3.8 Flash Next Uncensored
Qwen · AtomicChat
Params80M
Context256K
Q4_K_M93.9 GB
Vision
TI
TinyMistral 248M v2 Instruct
Tinymistral · M4-ai
Params248M
Context32K
Best fitQ8_0 0.9 GB
GGUF
DA
DanTagGen delta rev2
Dantaggen · KBlueLeaf
Params393M
Context2K
Best fitF16 2.1 GB
GGUF
LA
Laya
Laya · ggml-org
Params421M
Context8K
Best fitBF16 2.4 GB
GGUF
QW
XORTRON RICO v3
Qwen · darkc0de
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
SP
Spark X2.6 4B Abliterated
Spark · SC117
Params4.11B
Context1024K
Best fitQ6_K 5.1 GB
ReasoningTool use
QW
Qwen3 0.6b Abliterated
Qwen · mradermacher
Params596M
Context40K
Best fitQ5_K_S 1.9 GB
GGUF
GL
Models Zai Org GLM 4.6V Flash
GLM · MaziyarPanahi
Params9.4B
Context128K
Best fitQ5_K_M 7.9 GB
GGUF
MI
mistralai_Ministral 3 3B Instruct 2512 BF16
Mistral · lmstudio-community
Params3.43B
Context256K
Best fitQ8_0 5.0 GB
Vision
NE
NeoHorse 1 4B
Neohorse · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
ReasoningTool use
MU
Muse Glimmer 30B
Muse · bartowski
Params27.9B
Context128K
Best fitQ8_0 3.7 GB
Vision
GL
cerebras/GLM-4.7-Flash-REAP-23B-A3B
GLM · unsloth
Params23B
Context198K
Best fitTQ1_0 7.9 GB
GGUF
OR
Ornith 1.5 9B Heretic v2
Ornith · Thunder13240
Params8.95B
Context256K
Best fitQ5_K_M 8.0 GB
ReasoningVision
JI
JiRackUltra 1b
Jirackultra · CMSManhattan
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
MI
Devstral Small 2 24B Instruct 2512
Mistral · bartowski
Params23.6B
Context384K
Q4_K_M14.3 GB
Coding
QW
Qwen3 VL 2B Instruct
Qwen · ggml-org
Params1.72B
Context256K
Best fitQ8_0 3.3 GB
Vision
LL
codellama_codellama-7b-instruct-hf
Llama · TheBloke
Params6.74B
Context16K
Best fitQ3_K_S 7.7 GB
Coding

Other memory sizes

Keep browsing