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.
QW
Strand-Rust-Coder-14B-v1
Qwen · Mungert
Params14.8B
Context32K
Q4_K_M9.3 GB
QW
Fathom-Search-4B
Qwen · Mungert
Params4B
Context40K
Best fitQ8_0 6.0 GB
SK
SkyJM Edit 9B
Skyjm · mradermacher
Params8.95B
Context256K
Best fitQ3_K_S 5.8 GB
HU
Huihui3.5 67B A3B Abliterated
Huihui · mradermacher
Params67B
Context256K
Q4_K_M40.8 GB
HO
Sakura K2 Horizon 3.7B
Horizon · webmp3
Params5.06B
Context512K
Smallest2.2 GB
MI
Nous Hermes 2 Mistral 7B DPO
Mistral · NousResearch
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
MI
Ministral 3 14B Reasoning 2512 Absolute Heresy
Mistral · mradermacher
Params13.5B
Context256K
Best fitIQ2_XXS 5.8 GB
QW
Qwen2.5 Coder 0.5B
Qwen · bartowski
Params494M
Context32K
Best fitF16 1.6 GB
QW
Qwen3 8B Abliterated
Qwen · mradermacher
Params8.19B
Context40K
Best fitQ3_K_M 5.8 GB
LL
Llama3 8B Chinese Chat
Llama · Monor
Params8B
Context8K
Best fitQ3_K_L 5.9 GB
SP
Spark X2.6 4B Uncensored
Spark · mradermacher
Params4.11B
Context1024K
Best fitQ6_K 5.1 GB
TR
bluenipples_trion-m-7b
Trion · TheBloke
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
GR
Granite 3b Code Base
Granite · RichardErkhov
Params3.48B
Context2K
Best fitQ6_K 6.0 GB
NE
neo_7b_instruct_v0.1
Neo · legraphista
Params7.79B
Context8K
Best fitIQ2_M 6.0 GB
QW
Qwen3 0.6B Heretic Abliterated Uncensored
Qwen · Andycurrent
Params596M
Context40K
Q4_K_M0.4 GB
QW
rombos Replete Coder Qwen2 1.5b i1
Qwen · mradermacher
Params1.54B
Context128K
Best fitQ6_K 2.0 GB
YI
Mahou-1.3-yi-9B
Yi · mradermacher
Params8.83B
Context4K
Best fitQ3_K_L 6.0 GB
AD
AdaGuard 8B
Adaguard · mradermacher
Params8.19B
Context32K
Best fitQ3_K_M 5.8 GB
FA
Falcon3 1B Instruct
Falcon · bartowski
Params1.67B
Context8K
Best fitF16 4.4 GB
MI
Ministral-3-8B-Nymphaea-RP
Mistral · mradermacher
Params8.49B
Context256K
Best fitQ3_K_M 5.9 GB
MI
Mistral 7B Instruct v0.2
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ4_K_M 5.9 GB
AR
Arcee-Agent
Arcee · crusoeai
Params7.62B
Context128K
Best fitQ4_1 5.8 GB
QW
Qwen3.6 35B A3B REAM 160 ru agent
Qwen · WaveCut
Params23.1B
Context256K
Best fitQ1_0 5.4 GB
AY
aya-23-8B
Aya · legraphista
Params8B
Context8K
Best fitQ3_K 5.8 GB
AR
ArrowPro-7B-KillerWhale
Arrowpro · mmnga
Params7.24B
Context4K
Best fitQ4_K_M 5.9 GB
QW
Qwen3 32B VL GLM 4.7 Flash HI16 Heretic Uncensored Thinking
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
OL
OLMoE 1B 7B 0924 Instruct
OLMo · mradermacher
Params6.9B
Context4K
Best fitQ4_K_M 5.8 GB
QW
Qwen3.5 27B Abliterated Ko
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
GR
Granite 3b Code Instruct 2k
Granite · mradermacher
Params3.48B
Context2K
Best fitQ6_K 6.0 GB
QW
Qwen3-8B
Qwen · ggml-org
Params8.19B
Context40K
Best fitBF16 2.9 GB