Model Anatomy See what's inside open-weight AI models

Can I run Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF on a Mac with 36 GB?

Yes, just

Its RVN-Q6_K-multilingual-mtp file (22.5 GB) fits in the 24.0 GB a Mac with 36 GB can use, with room for ≈ 20K tokens of context.

Full analysis of Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF Everything that runs on Mac with 36 GB Get the RVN-Q6_K-multilingual-mtp file on Hugging Face
ollama run hf.co/0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF

Files and context on Mac with 36 GB

Each file of Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn Mac with 36 GB Context (16-bit)Context (8-bit)
BF1654.3 GBDoesn't fit——
F1654.3 GBDoesn't fit——
RVN-BF1653.8 GBDoesn't fit——
RVN-F1653.8 GBDoesn't fit——
RVN-Q8_0-multilingual-mtp29.0 GBDoesn't fit——
Q8_029.0 GBDoesn't fit——
RVN-Q8_0-multilingual28.6 GBDoesn't fit——
RVN-Q8_028.6 GBDoesn't fit——
RVN-Q6_K-multilingual-mtp22.5 GBTight20K39K
Q6_K22.5 GBTight20K39K
RVN-Q6_K-multilingual22.1 GBTight26K53K
RVN-Q6_K22.1 GBTight26K53K
RVN-Q5_K_M-multilingual-vision21.0 GBTight42K84K
RVN-Q5_K_M-vision21.0 GBTight42K84K
RVN-Q5_K_M-multilingual-mtp19.7 GBTight62K124K
Q5_K_M19.7 GBTight62K124K
RVN-Q5_K_M-multilingual19.2 GBTight69K138K
RVN-Q5_K_M19.2 GBTight69K138K
RVN-Q5_K_S-multilingual-mtp19.1 GBFits70K141K
Q5_K_S19.1 GBFits70K141K
RVN-Q4_K_M-multilingual-vision18.7 GBFits76K152K
RVN-Q4_K_M-vision18.7 GBFits76K152K
RVN-Q5_K_S-multilingual18.7 GBFits77K154K
RVN-Q5_K_S18.7 GBFits77K154K
RVN-Q4_K_M-multilingual-mtp17.0 GBFits102K204K
RVN-Q4_K_M-mtp17.0 GBFits102K204K
RVN-Q4_K_M-multilingual16.5 GBFits109K218K
Q4_K_M16.5 GBFits109K218K
RVN-Q4_K_M16.5 GBFits109K218K
IQ4_NL16.3 GBFits112K224K
RVN-IQ4_NL-multilingual-mtp16.3 GBFits113K226K
RVN-Q3_K_M-multilingual-vision16.2 GBFits114K228K
RVN-Q3_K_M-vision16.2 GBFits114K228K
RVN-Q4_K_S-multilingual-mtp16.0 GBFits116K233K
Q4_K_S16.0 GBFits116K233K
RVN-IQ4_NL15.9 GBFits119K237K
RVN-IQ4_NL-multilingual15.8 GBFits120K240K
IQ4_XS15.6 GBFits122K244K
RVN-Q4_K_S-multilingual15.6 GBFits123K246K
RVN-Q4_K_S15.6 GBFits123K246K
RVN-IQ4_XS-multilingual-mtp15.5 GBFits124K248K
RVN-IQ4_XS15.2 GBFits129K256K
RVN-IQ4_XS-multilingual15.1 GBFits131K256K
RVN-Q3_K_L-multilingual-mtp14.8 GBFits135K256K
Q3_K_L14.8 GBFits135K256K
RVN-Q3_K_L-multilingual14.3 GBFits142K256K
RVN-Q3_K_L14.3 GBFits142K256K
RVN-Q3_K_M-multilingual-mtp13.8 GBFits150K256K
Q3_K_M13.8 GBFits150K256K
RVN-Q3_K_M-multilingual13.3 GBFits157K256K
RVN-Q3_K_M13.3 GBFits157K256K
RVN-IQ3_M-multilingual-mtp13.0 GBFits161K256K
IQ3_M13.0 GBFits161K256K
RVN-IQ3_S-multilingual-mtp12.9 GBFits164K256K
IQ3_S12.9 GBFits164K256K
RVN-IQ3_M-multilingual12.6 GBFits168K256K
RVN-IQ3_M12.6 GBFits168K256K
RVN-Q3_K_S-multilingual-mtp12.5 GBFits169K256K
Q3_K_S12.5 GBFits169K256K
RVN-IQ3_S-multilingual12.4 GBFits170K256K
RVN-IQ3_S12.4 GBFits170K256K
RVN-IQ3_XS-multilingual-mtp12.4 GBFits170K256K
IQ3_XS12.4 GBFits170K256K
RVN-Q3_K_S-multilingual12.1 GBFits175K256K
RVN-Q3_K_S12.1 GBFits175K256K
RVN-IQ3_XS-multilingual12.0 GBFits177K256K
RVN-IQ3_XS12.0 GBFits177K256K
RVN-Qwen3.8-27B-Heretic-GSQ-RCO-IQ3_S11.8 GBFits180K256K
RVN-IQ3_XXS-multilingual-mtp11.6 GBFits182K256K
IQ3_XXS11.6 GBFits182K256K
RVN-IQ3_XXS-multilingual11.2 GBFits189K256K
RVN-IQ3_XXS11.2 GBFits189K256K
RVN-Q2_K-multilingual-mtp11.2 GBFits189K256K
Q2_K11.2 GBFits189K256K
RVN-Q2_K-multilingual10.7 GBFits196K256K
RVN-Q2_K10.7 GBFits196K256K
RVN-Q2_K_S-multilingual-mtp10.7 GBFits196K256K
Q2_K_S10.7 GBFits196K256K
RVN-IQ2_M-multilingual-mtp10.5 GBFits200K256K
IQ2_M10.5 GBFits200K256K
RVN-Q2_K_S-multilingual10.2 GBFits203K256K
RVN-Q2_K_S10.2 GBFits203K256K
RVN-IQ2_M-multilingual10.0 GBFits206K256K
RVN-IQ2_M10.0 GBFits206K256K
RVN-IQ2_S-multilingual-mtp9.81 GBFits209K256K
IQ2_S9.81 GBFits209K256K
RVN-IQ2_XS-multilingual-mtp9.54 GBFits213K256K
IQ2_XS9.54 GBFits213K256K
RVN-IQ2_S-multilingual9.36 GBFits216K256K
RVN-IQ2_S9.36 GBFits216K256K
RVN-IQ2_XS-multilingual9.09 GBFits220K256K
RVN-IQ2_XS9.09 GBFits220K256K
RVN-IQ2_XXS-multilingual-mtp8.88 GBFits223K256K
IQ2_XXS8.88 GBFits223K256K
RVN-IQ2_XXS-multilingual8.43 GBFits230K256K
RVN-IQ2_XXS8.43 GBFits230K256K
RVN-IQ1_M-multilingual-mtp8.08 GBFits235K256K
IQ1_M8.08 GBFits235K256K
RVN-IQ1_M-multilingual7.63 GBFits242K256K
RVN-IQ1_M7.63 GBFits242K256K
RVN-IQ1_S-multilingual-mtp7.60 GBFits242K256K
IQ1_S7.60 GBFits242K256K
RVN-IQ1_S-multilingual7.15 GBFits249K256K
RVN-IQ1_S7.15 GBFits249K256K

Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF on other hardware

Popular models that run on Mac with 36 GB

Assumes 67% of the Mac's memory is usable (macOS's default limit for the GPU; it can be raised) and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.