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.
NY
Nyakura CausalLM RP 34B i1
Nyakura · mradermacher
Params34.4B
Context195K
Best fitQ6_K 30.7 GB
QW
Qwen3.8 27B TQ
Qwen · YTan2000
Params27.3B
Context256K
Smallest0.8 GB
LL
togethercomputer_llama-2-7b-32k-instruct
Llama · TheBloke
Params6.74B
Context32K
Best fitQ8_0 12.0 GB
TA
UI TARS 7B DPO
Tars · bartowski
Params7.62B
Context32K
Best fitF32 31.4 GB
MI
Mixtral_7Bx2_MoE_13B
Mistral · mradermacher
Params12.9B
Context32K
Best fitQ6_K 12.1 GB
MI
Sydney_Pirate_Mistral_7b
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
ME
q-bert_metamath-cybertron-starling
Metamath · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
LL
CodeLlama 70b Instruct Hf
Llama · mradermacher
Params69B
Context4K
Best fitIQ3_XS 31.5 GB
ST
StarCoder
StarCoder · mradermacher
Params15.5B
Context8K
Best fitQ6_K 13.6 GB
FL
Sakura FLUX.3 Image Klein PromptUpsampler Uncensored
Flux · webmp3
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
HO
Holo4 35B A3B
Holo · mradermacher
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
BO
Boulesis v2.1 26B A4B HeadTune
Boulesis · mradermacher
Params26B
Context256K
Best fitQ6_K 31.8 GB
QW
Qwen3 4B toolcalling gguf codex
Qwen · Manojb
Params4B
Context256K
Smallest4.3 GB
QW
Qwen3.5 4B
Qwen · dahara1
Params4.21B
Context256K
Best fitBF16 10.0 GB
GE
Gemma 4 12B It Uncensored Heretic
Gemma · mradermacher
Params11.9B
Context256K
Best fitQ8_0 26.1 GB
MI
ANITA NEXT 24B Dolphin Mistral UNCENSORED ITA
Mistral · mradermacher
Params23.6B
Context40K
Best fitQ6_K 21.2 GB
NE
NVIDIA Nemotron 3.5 Bolt E4B
Nemotron · bartowski
Params7.52B
Context64K
Best fitBF16 17.0 GB
QW
Swift 1.5 Qwen3.8 27b Heretic
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ6_K 25.1 GB
DI
digital socrates 7b i1
Digital · mradermacher
Params6.74B
Context4K
Best fitQ6_K 10.3 GB
GE
Mahou-1.3-gemma2-9B
Gemma · mradermacher
Params9.24B
Context8K
Best fitQ6_K 10.9 GB
DE
MultiPL-T-DeepSeekCoder_33b
DeepSeek · mradermacher
Params33.3B
Context16K
Best fitQ6_K 29.9 GB
AU
Aura Prototype 26B A4B
Aura · mradermacher
Params26B
Context256K
Best fitQ6_K 31.8 GB
KI
Huihui Kimi Linear 48B A3B Instruct Abliterated
Kimi · mradermacher
Params49.1B
Context1024K
Best fitQ3_K_S 31.0 GB
SM
SmolLM 135M
SmolLM · QuantFactory
Params135M
Context2K
Best fitQ2_K 0.8 GB
DE
DAN L3 R1 8B
DeepSeek · UnfilteredAI
Params8B
Context128K
Best fitF16 17.6 GB
PE
PentaCoder 9B
Pentacoder · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
WI
ehartford_wizard-vicuna-30b-uncensored
Wizard · TheBloke
Params32.5B
Context2K
Best fitQ4_K_S 32.0 GB
GE
Gemopus 4 26B A4B it Preview APEX
Gemopus · mudler
Params25.2B
Context256K
Smallest13.0 GB
LF
LFM2.5-24B-A2B-Preview
Lfm · AtomicChat
Params24B
Context128K
Best fitQ8_0 28.9 GB
QW
QwenPaw Flash 9B heretic MTP
Qwen · SC117
Params456M
Context256K
Best fitF16 20.0 GB