GGUF models that fit in 4 GB
79024 GGUF language models have at least one quant whose estimated memory use is 4 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 1280000K tokens.
QW
ThinkingCap Qwen3.8 27B abliterated
Qwen · IstroSec
Params27.3B
Context256K
Q4_K_M17.0 GB
QW
Qwen2.5 Coder 14B E2E Tests
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
PY
Pythia 1.4b Deduped
Pythia · mradermacher
Params1.41B
Context2K
Best fitQ6_K 3.3 GB
QE
qev 0.8b
Qev · labqoat
Params752M
Context256K
Best fitBF16 2.4 GB
LL
tiny random LlamaForCausalLM
Llama · aladar
Params1M
Context2K
Smallest0.0 GB
QW
OpenChat 3.5 7B Qwen v2.0
Qwen · mradermacher
Params7.24B
Context8K
Best fitIQ2_S 3.9 GB
MI
Ministral 3 8B Reasoning 2512 Esper3.1
Mistral · mradermacher
Params8.49B
Context256K
Best fitIQ1_M 3.9 GB
QW
Qwopus3.8 27B Flash V2 Apostate Uncensored
Qwopus · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
QW
Qwen2.5 7B Instruct
Qwen · RichardErkhov
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
GE
Gemma 3 1b It Qat
Gemma · bartowski
Params1B
Context32K
Best fitBF16 2.7 GB
MI
Hermes-2-Pro-Mistral-7B-infinity
Mistral · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
RA
al rasheed ai
Rasheed · alpha-coder-great
Params3B
Context128K
Best fitQ4_K_M 3.5 GB
QW
QwenDGAF V3 4B
Qwen · hecan3d
Params4B
Context40K
Best fitQ3_K_M 3.8 GB
JA
Javi0.3 2B
Javi · mradermacher
Params1.94B
Context256K
Best fitQ6_K 2.5 GB
LL
gpt 4o distil Llama 3.3 70B Instruct PaperWitch heresy i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
IN
OpenChat 3.5 7B InternLM v2.0
InternLM · mradermacher
Params7.24B
Context8K
Best fitIQ2_S 3.9 GB
QW
FlashModel Qwen 3.6 35B A3B Maxed
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
GE
medgap gemma 4 12b
Gemma · protocolsyncllc
Params11.9B
Context256K
Best fitQ8_0 2.0 GB
XO
XORTRON AgentRICO
Xortron · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
MI
Mistral Syndicate 7B
Mistral · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
NE
Nehuronion Dvt 9b
Nehuronion · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
QW
Qwen3.8-27B-DFlash2
Qwen · magnitudedev
Params1.92B
Context256K
Best fitQ8_0 2.7 GB
OR
Ornith 1.5 122B
Ornith · mradermacher
Params125B
Context256K
Q4_K_M75.8 GB
QW
Qwen3.6 35B A3B Uncensored Genesis Final Safetensors
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
QW
qwen3loop 0.6b sft deep supervision v1
Qwen · Lordnyx
Params596M
Context40K
Best fitF16 3.6 GB
DE
deepseek r1
DeepSeek · cortexso
Params70.6B
Context128K
Best fitQ2_K 3.9 GB
OP
openPangu Embedded 7B V1.1
Openpangu · mradermacher
Params8.03B
Context32K
Best fitIQ1_M 3.9 GB
FA
Falcon H1 7B Instruct
Falcon · tiiuae
Params7.59B
Context256K
Best fitIQ3_XXS 3.9 GB
EC
EchoVLM_v2
Echovlm · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
GPT neo Custom 7B
Qwen · Szymon-Wachelko
Params7.6B
Context32K
Best fitQ2_K 4.0 GB