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.
TI
tinygemma3
Tinygemma · ggml-org
Params38M
Context128K
Best fitQ8_0 0.7 GB
MO
moondream2 multiformat
Moondream · Serkan007
Params—
Context—
Best fitQ4_K_M 0.5 GB
MI
Hermes 2 Pro Mistral 7B
Mistral · NousResearch
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
QW
Qwen3 30B A3B Instruct 2507
Qwen · bartowski
Params30.5B
Context256K
Best fitQ6_K_L 26.6 GB
QW
Qwen3.6 40B Claude 4.6 Opus Deckard Heretic Uncensored Thinking NEO CODE Di IMatrix MAX
Qwen · DavidAU
Params39.1B
Context256K
Best fitQ5_K_M 31.9 GB
QW
Qwen3-Next-80B-A3B-Instruct
Qwen · unsloth
Params80B
Context256K
Best fitQ2_K_XL 31.4 GB
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · unsloth
Params7.62B
Context128K
Best fitF16 16.2 GB
DE
DeepSeek R1 Distill Qwen 14B
DeepSeek · bartowski
Params14.8B
Context128K
Best fitF16 31.7 GB
XI
Xing4.0 29B A4B
Xing · Venastine-Research
Params31.2B
Context256K
Best fitQ6_K 26.9 GB
MI
Mistral-Small-3.2-24B-Instruct-2506
Mistral · unsloth
Params23.6B
Context128K
Best fitQ8_K_XL 30.8 GB
OP
openthaigpt1.5 7b instruct
Openthaigpt · openthaigpt
Params7.62B
Context32K
Best fitF16 16.2 GB
QW
Models Qwen Qwen3 0.6B
Qwen · MaziyarPanahi
Params752M
Context40K
Q4_K_M0.5 GB
QW
Qwen3.8 27B
Qwen · AtomicChat
Params27.3B
Context256K
Best fitQ8_0 31.6 GB
NO
nomic-embed-text-v2-moe
Nomic · nomic-ai
Params475M
Context512
Best fitF32 2.7 GB
QW
Qwen3Vl 30b A3B Instruct
Qwen · Qwen
Params30.5B
Context256K
Best fitQ4_K_M 19.9 GB
QW
Qwen3-14B
Qwen · unsloth
Params14.8B
Context40K
Best fitBF16 31.4 GB
TI
tinyllama_tinyllama-1.1b-chat-v1.0
Tinyllama · TheBloke
Params1.1B
Context2K
Best fitQ8_0 1.9 GB
QW
Models Qwen Qwen3 4B
Qwen · MaziyarPanahi
Params4B
Context40K
Q4_K_M2.5 GB
SM
SmolLM2 135M Instruct
SmolLM · unsloth
Params135M
Context8K
Best fitF16 1.0 GB
LL
Llama 4 Scout 17B 16E Instruct
Llama · bartowski
Params108B
Context10240K
Best fitIQ1_M 28.4 GB
GE
gemma 4 E2B it qat
Gemma · unsloth
Params4.63B
Context128K
Best fitQ4_K_XL 3.2 GB
QW
Qwen3.6-27B
Qwen · unsloth
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
CY
Huihui CyberStrike OffSec 35B Abliterated
Cyberstrike · huihui-ai
Params35.5B
Context256K
Best fitQ6_K 30.4 GB
QW
Huihui Qwen3.5 4B Abliterated
Qwen · mradermacher
Params4.21B
Context256K
Best fitF16 10.0 GB
QW
Qwen3Vl 32b Instruct
Qwen · Qwen
Params32.8B
Context256K
Best fitQ4_K_M 22.4 GB
QW
Models Qwen Qwen3 14B
Qwen · MaziyarPanahi
Params14.8B
Context40K
Q4_K_M9.0 GB
GE
Gemma 4 26B A4B It
Gemma · bartowski
Params25.2B
Context256K
Best fitQ6_K_L 31.6 GB
QW
Models Qwen Qwen3 1.7B
Qwen · MaziyarPanahi
Params2.03B
Context40K
Q4_K_M1.3 GB
GE
Gemma 4 26B A4B
Gemma · lmstudio-community
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
AC
ace step 1.5 gguf merge models
Ace · scragnog
Params5B
Context32K
Best fitBF16 11.6 GB