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.
MI
Pixtral
Mistral · bartowski
Params12.2B
Context1000K
Best fitQ3_K_M 7.9 GB
TE
tenyx_tenyxchat-7b-v1
Tenyxchat · TheBloke
Params7.24B
Context8K
Best fitQ6_K 7.5 GB
PY
Pythia 6.9b Deduped
Pythia · mradermacher
Params6.86B
Context2K
Best fitIQ3_XS 7.8 GB
HA
Haru Kanana 8b
Haru · mradermacher
Params8B
Context32K
Best fitQ5_K_M 7.3 GB
YI
Yi-1.5-9B-Chat-16K
Yi · mradermacher
Params8.83B
Context16K
Best fitQ5_K_M 7.6 GB
SM
nisten/Biggie-SmoLlm-0.15B-Base
SmolLM · nisten
Params152M
Context2K
Best fitBF16 1.1 GB
QW
QiMing Holos Plus Qwen3 14B
Qwen · mradermacher
Params14.8B
Context40K
Best fitIQ3_XXS 7.8 GB
ST
L3-8B-Stheno-v3.2
Stheno · mradermacher
Params8B
Context8K
Best fitQ5_K_M 7.3 GB
MI
meta-math_metamath-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
ZA
Zarafusionex 1.1 L2 7B
Zarafusionex · TheBloke
Params6.74B
Context4K
Best fitQ3_K_S 7.7 GB
MI
dolphin-2.9.1-mixtral-1x22b
Mistral · mradermacher
Params22.2B
Context64K
Best fitIQ1_M 7.6 GB
QW
Jan-v2-VL-high
Qwen · Mungert
Params8.2B
Context256K
Best fitQ5_K_M 8.0 GB
QW
Qwen3.6 35B A3B Uncensored Aggressive
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
QW
Qwen3 VL 32B Instruct Ultra Uncensored Heretic
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
HO
Holo4 27B Abliterix
Holo · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
QW
Qwen2.5 Coder 0.5B Instruct Abliterated
Qwen · bartowski
Params494M
Context32K
Best fitF16 1.6 GB
MI
Mistral Nemo 12B Instruct
Mistral · mradermacher
Params12.2B
Context1000K
Best fitQ3_K_M 7.9 GB
TO
TowerInstruct 7B v0.1
Towerinstruct · TheBloke
Params6.74B
Context4K
Best fitQ3_K_S 7.7 GB
QW
Qwen3 8B Heretic
Qwen · mradermacher
Params8.19B
Context40K
Best fitQ5_K_M 7.6 GB
GE
Gemma 3 it 4B Uncensored DBL X
Gemma · DavidAU
Params4.26B
Context128K
Best fitQ8_0 6.3 GB
GP
GPT OSS Cybersecurity 20B Merged Heretic
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
YI
Hermes-2.5-Yi-1.5-9B-Chat
Yi · mradermacher
Params8.83B
Context4K
Best fitQ5_K_M 7.6 GB
QW
dolphin-2.9.2-qwen2-7b
Qwen · dphn
Params7.62B
Context128K
Best fitQ6_K 7.2 GB
GE
Gemma 3 270m It
Gemma · bartowski
Params268M
Context32K
Best fitBF16 1.2 GB
SP
SpydazWebAI_Human_AGI
Spydazwebai · mradermacher
Params7.24B
Context512K
Best fitQ6_K 7.5 GB
QW
Qwythos 9B v2
Qwythos · mradermacher
Params9.2B
Context1024K
Best fitQ4_K_M 7.4 GB
QW
Qwen3 VL 8B Abliterated Caption It
Qwen · mradermacher
Params8.19B
Context256K
Best fitQ5_K_M 7.6 GB
GE
gemma 4 e2b yemeni arabic assistant
Gemma · yemeni-ai-lab
Params4.63B
Context128K
Best fitMXFP4_MOE 6.0 GB
AH
Ahma 7B
Ahma · mradermacher
Params7B
Context2K
Best fitIQ3_S 7.9 GB
MI
Infinity Instruct 7M 0729 Mistral 7B
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB