GGUF models that fit in 32 GB
198257 GGUF language models have at least one quant whose estimated memory use is 32 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.
QW
Qwen3VL 8B Uncensored HauhauCS Balanced
Qwen · HauhauCS
Params8.2B
Context256K
Best fitBF16 18.1 GB
NE
Nex N2 Mini
Nex · bartowski
Params34.7B
Context256K
Best fitQ6_K_L 31.5 GB
UM
BojroPromptMaster uncensored v2 8B
Umbral · bojrodev
Params8B
Context8K
Best fitBF16 17.6 GB
QW
Qwen3.5 9B BOS Q8 NonThinking
Qwen · shaban2024
Params8.95B
Context256K
Smallest9.5 GB
SM
SmolLM2 135M
SmolLM · prithivMLmods
Params135M
Context8K
Best fitF16 1.0 GB
PH
Phi 4 Mini Instruct
Phi · lmstudio-community
Params3.84B
Context128K
Best fitQ8_0 5.7 GB
TE
Ternary Bonsai 4B
Ternary · prism-ml
Params4B
Context32K
Best fitF16 9.8 GB
OC
Occamy 1.0 APEX I MiniPlus V2.1
Occamy · IsValorum
Params34.7B
Context256K
Q4_K_M1.3 GB
QW
Qwen3.8 27B Whitehat
Qwen · QuaduxIT
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
QW
MiMo V2.6 Distill Qwen 9B heretic
Qwen · saidutta69
Params8.95B
Context256K
Best fitF16 19.5 GB
HE
0 hero Matter 0.2 7B
Hero · RichardErkhov
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
QW
Qwen3.8 Cyber RedTeam Surgical Abliterated
Qwen · mradermacher
Params27B
Context256K
Best fitQ8_0 31.2 GB
LL
llama3.1 airoboros3.2 QDT 8B
Llama · bartowski
Params8B
Context128K
Best fitF16 17.6 GB
JE
JEV 35B
Jev · mradermacher
Params35.5B
Context256K
Best fitQ6_K 30.4 GB
IN
InternVL3_5 2B
Internvl · bartowski
Params2.03B
Context40K
Best fitBF16 5.5 GB
QW
Qwen3 30B A3B
Qwen · 6block
Params30.5B
Context40K
Best fitQ6_K 26.4 GB
QW
Swift 1.5 Qwen3.8 27b MXFP4
Qwen · tsaipifong
Params27.3B
Context256K
Best fitMXFP4 18.8 GB
IN
Ingot XI 27B Q2
Ingot · dendriteholdings
Params26.9B
Context256K
Smallest7.2 GB
GL
GLM-4.7-Flash-Uncensored-HauhauCS-Aggressive
GLM · HauhauCS
Params30B
Context198K
Best fitQ6_K 26.0 GB
LL
LIama 3.2 test
Llama · bhanuripranathi
Params3.21B
Context128K
Best fitQ4_K_M 3.5 GB
QW
Qwen3.8 Flash Next
Qwen · AesSedai
Params180B
Context256K
Q4_K_M116.1 GB
AR
AREX Turbo
Arex · bartowski
Params4.2B
Context256K
Best fitBF16 10.0 GB
MA
magnum v4 12b
Magnum · anthracite-org
Params12.2B
Context1000K
Best fitQ8_0 14.9 GB
KI
Kimi VL A3B Thinking 2506
Kimi · ggml-org
Params16B
Context128K
Best fitQ8_0 18.0 GB
WI
Wicked Stuff 26B A4B v2.0 Final
Wicked · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
BO
Borealis Open 27b
Borealis · mradermacher
Params27B
Context128K
Best fitQ6_K 26.8 GB
GL
GLM 4 32B 0414
GLM · bartowski
Params32.6B
Context32K
Best fitQ6_K_L 28.2 GB
QW
Qwen3.8 27B Uncensored
Qwen · shsunshining
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
QW
Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
LF
LFM2.5-8B-A1B-Uncensored-Gaston
Lfm · gaston-parravicini
Params8.47B
Context125K
Best fitQ8_0 11.1 GB