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

Can I run Nanbeige4.3-33B on a Mac with 36 GB?

Yes, with a GGUF version

The published weights are too big, but the Nanbeige4.3-33B-AD-Q5_K_M-Q4_K_M file from AtomicChat/Nanbeige4.3-33B-GGUF (22.6 GB) fits, with room for ≈ 6K tokens of context.

Full analysis of Nanbeige4.3-33B Everything that runs on Mac with 36 GB Get the Nanbeige4.3-33B-AD-Q5_K_M-Q4_K_M file on Hugging Face
ollama run hf.co/AtomicChat/Nanbeige4.3-33B-GGUF

Files and context on Mac with 36 GB

Each file of Nanbeige4.3-33B (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)
As published66.2 GBDoesn't fit——
BF16bartowski/Nanbeige_Nanbeige4.3-33B-GGUF66.2 GBDoesn't fit——
Q8_0bartowski/Nanbeige_Nanbeige4.3-33B-GGUF35.2 GBDoesn't fit——
Q6_K_Lbartowski/Nanbeige_Nanbeige4.3-33B-GGUF30.4 GBDoesn't fit——
Q6_Kbartowski/Nanbeige_Nanbeige4.3-33B-GGUF29.0 GBDoesn't fit——
Q6_K_Sbartowski/Nanbeige_Nanbeige4.3-33B-GGUF27.8 GBDoesn't fit——
Q5_K_Mbartowski/Nanbeige_Nanbeige4.3-33B-GGUF25.1 GBDoesn't fit——
Q5_K_Sbartowski/Nanbeige_Nanbeige4.3-33B-GGUF23.7 GBDoesn't fit2K3K
Q4_K_Lbartowski/Nanbeige_Nanbeige4.3-33B-GGUF22.3 GBTight8K15K
Q4_1bartowski/Nanbeige_Nanbeige4.3-33B-GGUF21.2 GBTight13K26K
IQ4_NLbartowski/Nanbeige_Nanbeige4.3-33B-GGUF20.9 GBTight14K29K
Q4_K_Mbartowski/Nanbeige_Nanbeige4.3-33B-GGUF20.8 GBTight15K29K
Q4_K_Sbartowski/Nanbeige_Nanbeige4.3-33B-GGUF19.7 GBTight20K39K
Q4_0bartowski/Nanbeige_Nanbeige4.3-33B-GGUF19.3 GBTight21K43K
IQ4_XSbartowski/Nanbeige_Nanbeige4.3-33B-GGUF18.6 GBFits25K49K
IQ3_Mbartowski/Nanbeige_Nanbeige4.3-33B-GGUF17.8 GBFits28K57K
Q3_K_Lbartowski/Nanbeige_Nanbeige4.3-33B-GGUF17.3 GBFits31K62K
Q3_K_Mbartowski/Nanbeige_Nanbeige4.3-33B-GGUF15.9 GBFits37K74K
IQ3_XSbartowski/Nanbeige_Nanbeige4.3-33B-GGUF15.2 GBFits40K81K
Q3_K_Sbartowski/Nanbeige_Nanbeige4.3-33B-GGUF15.2 GBFits40K81K
IQ3_XXSbartowski/Nanbeige_Nanbeige4.3-33B-GGUF14.5 GBFits44K87K
Q2_Kbartowski/Nanbeige_Nanbeige4.3-33B-GGUF13.5 GBFits48K96K
IQ2_Mbartowski/Nanbeige_Nanbeige4.3-33B-GGUF12.2 GBFits54K108K
IQ2_Sbartowski/Nanbeige_Nanbeige4.3-33B-GGUF11.2 GBFits59K118K
IQ2_XSbartowski/Nanbeige_Nanbeige4.3-33B-GGUF10.6 GBFits61K123K
IQ2_XXSbartowski/Nanbeige_Nanbeige4.3-33B-GGUF10.1 GBFits64K128K
Q8_0AtomicChat/Nanbeige4.3-33B-GGUF35.2 GBDoesn't fit——
Q6_KAtomicChat/Nanbeige4.3-33B-GGUF30.1 GBDoesn't fit——
Q5_KAtomicChat/Nanbeige4.3-33B-GGUF27.9 GBDoesn't fit——
Q5_K_MAtomicChat/Nanbeige4.3-33B-GGUF24.7 GBDoesn't fit——
Nanbeige4.3-33B-Q5_K_MAtomicChat/Nanbeige4.3-33B-GGUF23.5 GBDoesn't fit2K5K
Nanbeige4.3-33B-AD-Q5_K_M-Q4_K_MAtomicChat/Nanbeige4.3-33B-GGUF22.6 GBTight6K13K
Q4_K_MAtomicChat/Nanbeige4.3-33B-GGUF21.2 GBTight13K26K
IQ4_XSAtomicChat/Nanbeige4.3-33B-GGUF20.3 GBTight17K33K
IQ3_SAtomicChat/Nanbeige4.3-33B-GGUF17.1 GBFits32K64K
IQ3_XXSAtomicChat/Nanbeige4.3-33B-GGUF14.9 GBFits42K83K
IQ2_SAtomicChat/Nanbeige4.3-33B-GGUF13.7 GBFits47K94K

Nanbeige4.3-33B 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.