GGUF models that fit in 6 GB
123636 GGUF language models have at least one quant whose estimated memory use is 6 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.
NO
nomic ai nomic embed code
Nomic · bartowski
Params7.1B
Context32K
Best fitQ5_K_M 6.0 GB
EK
Ekbasis Skopos 27B
Ekbasis · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
AI
aiXcompact 4B
Aixcompact · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.1 GB
IN
Internvl3-78B-Instruct
Internvl · unsloth
Params72.7B
Context32K
Best fitIQ1_M 5.4 GB
IN
Internlm2 Math Plus 1_8b
InternLM · mradermacher
Params1.89B
Context8K
Best fitQ6_K 2.9 GB
PH
Phi 3 Mini 4k Instruct
Phi · second-state
Params3.82B
Context4K
Q4_K_M2.4 GB
RW
rwitz_go-bruins
Rwitz · TheBloke
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
SM
SmolLM2 360M Instruct
SmolLM · unsloth
Params362M
Context8K
Best fitF16 1.6 GB
NE
models--automerger--NeuralsirkrishnaInex12-7B
Neuralsirkrishna · MaziyarPanahi
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
AS
AstaBrief_8B
Astabrief · mradermacher
Params8.2B
Context40K
Best fitQ3_K_M 5.8 GB
QW
Huihui Qwen3 30B A3B Thinking 2507 Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
QW
Qwen3.5 9b Uncensored
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ3_K_S 5.8 GB
MI
Magistral Small 2509
Mistral · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
LL
Llama-3-8B-Instruct-262k
Llama · crusoeai
Params8B
Context256K
Best fitQ3_K_L 5.9 GB
QW
Qwen3.5 4B
Qwen · Smoffyy
Params4.21B
Context256K
Best fitQ5_K_M 4.6 GB
SH
Shaylah Darija 4b Merged
Shaylah · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.1 GB
ZO
Zoro i1
Zoro · mradermacher
Params4.84B
Context256K
Best fitQ6_K 5.6 GB
NE
Nex N2.5 Pro
Nex · bartowski
Params396B
Context256K
Q4_K_M250.8 GB
TR
TranslatePsy AfriSLM 0.8B
Translatepsy · mradermacher
Params1.01B
Context256K
Best fitQ6_K 1.8 GB
GE
Gemma 3 4B it Uncensored
Gemma · lemuralabs
Params3.88B
Context128K
Best fitQ8_0 5.8 GB
DO
DoItYourself v1 2B
Doityourself · theprint
Params1.94B
Context256K
Best fitBF16 4.8 GB
HE
Hermes 2 DPO WestLake 7B v2
Hermes · mradermacher
Params7.24B
Context32K
Best fitQ4_K_S 5.9 GB
QW
Twi Qwen v1 Merged
Qwen · mradermacher
Params8.95B
Context256K
Best fitIQ3_S 6.0 GB
ME
MechVL 4B RL
Mechvl · mradermacher
Params4.41B
Context256K
Best fitQ6_K 5.3 GB
GR
Granite 4.0 H Small
Granite · bartowski
Params32.2B
Context1024K
Q4_K_M19.7 GB
SO
SOR ColdBrew 12B Think RP Base
Sor · mradermacher
Params12.2B
Context1000K
Best fitIQ2_S 6.0 GB
SN
SniffyOtter 7B
Sniffyotter · RichardErkhov
Params7.24B
Context8K
Best fitQ4_K 5.9 GB
MI
Hermes-2-Pro-Mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
QW
Qwen3.8 27B OBLITERATED Mythos Class Agentic
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
GP
Gpt Oss 20b Unsloth Puzzle V2
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB