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.
MI
MiniCPM OCR Jev
MiniCPM · openbmb
Params1.88B
Context256K
Best fitF16 4.7 GB
LI
vllm-d3-lite
Lite · ggml-org
Params1.01B
Context256K
Best fitBF16 2.9 GB
AE
AesCode 32B
Aescode · bartowski
Params32.8B
Context256K
Q4_K_M20.5 GB
DA
Darwin 27B RSI
Darwin · bartowski
Params27B
Context256K
Q4_K_M17.2 GB
QW
Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-Aggressive
Qwen · HauhauCS
Params4B
Context256K
Best fitQ8_0 6.0 GB
GE
Ablation 187 Gemma3.Webnovels.Test.Gemma 3 4b
Gemma · mradermacher
Params3.88B
Context128K
Best fitQ8_0 5.8 GB
GR
Granite 4.0 Micro
Granite · ibm-granite
Params3.4B
Context128K
Best fitQ4_K_M 6.0 GB
JI
jinen-v1-xsmall-hf
Jinen · togatogah
Params36M
Context1K
Best fitF16 0.7 GB
PH
phi3.5 gutenberg 4B
Phi · bartowski
Params3.82B
Context128K
Best fitQ3_K_XL 5.9 GB
SE
Sexpedition MS3.2 24B
Sexpedition · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
CO
Confucius4 R2T2
Confucius · netease-youdao
Params1.72B
Context64K
Best fitF16 4.9 GB
TE
Ternary Bonsai 1.7B
Ternary · prism-ml
Params1.72B
Context32K
Best fitF16 4.9 GB
QW
Huihui Qwen3 8B Abliterated v2
Qwen · mradermacher
Params8.19B
Context40K
Best fitQ3_K_M 5.8 GB
DA
L3 Dark Planet 8B
Dark · DavidAU
Params8B
Context8K
Best fitQ3_K_M 5.8 GB
ST
stablelm 2 zephyr 1 6b
Stablelm · stabilityai
Params1.64B
Context4K
Smallest1.0 GB
QW
Qwen2.5 VL 7B Abliterated Caption It
Qwen · mradermacher
Params7.62B
Context125K
Best fitQ4_K_M 5.7 GB
LL
Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps
Llama · NousResearch
Params3.21B
Context128K
Best fitQ8_0 4.9 GB
QW
Qwen3 VL Reranker 8B
Qwen · mradermacher
Params8.19B
Context256K
Best fitQ3_K_M 5.8 GB
OR
Ornith1.0 9B 3MPER0RR Abliterated
Ornith · mradermacher
Params8.95B
Context256K
Best fitQ3_K_S 5.9 GB
ON
OneJev 4B
Onejev · mradermacher
Params4.84B
Context256K
Best fitQ6_K 5.6 GB
LF
LFM2.5 VL 3B Uncensored
Lfm · SC117
Params2.7B
Context125K
Best fitQ8_0 5.4 GB
PH
Phi 4 Mini Reasoning
Phi · lmstudio-community
Params3.84B
Context128K
Best fitQ8_0 5.7 GB
ST
berkeley-nest_starling-lm-7b-alpha
Starling · TheBloke
Params7.24B
Context8K
Best fitQ4_K_M 5.9 GB
QW
Qwen3 14B ARPO DeepSearch
Qwen · mradermacher
Params14.8B
Context40K
Best fitIQ1_M 5.7 GB
QW
Qwen3.8-27B-DFlash2-ternary-bonsai2-r3
Qwen · naklitechie
Params1.92B
Context256K
Best fitQ4_K_M 1.8 GB
QW
Qwen3.5 4B Heretic
Qwen · darrellbest
Params4.33B
Context256K
Best fitQ4_K_M 4.4 GB
MY
Mythos v2 9b
Mythos · fableforge-ai
Params9.2B
Context256K
Best fitQ3_K_S 6.0 GB
HO
Holo 3.1 4B
Holo · mradermacher
Params4.84B
Context256K
Best fitQ6_K 5.6 GB
TO
tokyotech llm Swallow MS 7b instruct v0.1
Tokyotech · mmnga
Params7.33B
Context4K
Best fitQ4_K_M 6.0 GB
QW
qwen2-7b-instruct
Qwen · Qwen
Params7.62B
Context32K
Best fitQ4_K_M 5.7 GB