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

Can I run Swift-Qwen3.8-27b on a Mac with 32 GB?

Yes, with a GGUF version

The published weights are too big, but the Q5_K_M file from ukisai/Swift-Qwen3.8-27B-GGUF (20.2 GB) fits, with room for ≈ 15K tokens of context.

Full analysis of Swift-Qwen3.8-27b Everything that runs on Mac with 32 GB Get the Q5_K_M file on Hugging Face
ollama run hf.co/ukisai/Swift-Qwen3.8-27B-GGUF:Q5_K_M

Files and context on Mac with 32 GB

Each file of Swift-Qwen3.8-27b (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 32 GB Context (16-bit)Context (8-bit)
As published55.6 GBDoesn't fit——
F16ukisai/Swift-Qwen3.8-27B-GGUF54.7 GBDoesn't fit——
Q8_0ukisai/Swift-Qwen3.8-27B-GGUF29.1 GBDoesn't fit——
Q6_K_Lukisai/Swift-Qwen3.8-27B-GGUF25.2 GBDoesn't fit——
Q6_K_Sukisai/Swift-Qwen3.8-27B-GGUF23.1 GBDoesn't fit——
Q6_Kukisai/Swift-Qwen3.8-27B-GGUF22.9 GBDoesn't fit——
Q5_K_Mukisai/Swift-Qwen3.8-27B-GGUF20.2 GBTight15K29K
Q5_K_Sukisai/Swift-Qwen3.8-27B-GGUF19.8 GBTight21K42K
Q4_K_Lukisai/Swift-Qwen3.8-27B-GGUF19.0 GBTight32K64K
Q4_K_Mukisai/Swift-Qwen3.8-27B-GGUF18.0 GBTight47K94K
IQ4_NLukisai/Swift-Qwen3.8-27B-GGUF17.7 GBTight53K105K
Q4_1ukisai/Swift-Qwen3.8-27B-GGUF17.5 GBTight54K109K
Q4_K_Sukisai/Swift-Qwen3.8-27B-GGUF16.6 GBFits69K137K
Q4_0ukisai/Swift-Qwen3.8-27B-GGUF16.0 GBFits78K155K
IQ4_XSukisai/Swift-Qwen3.8-27B-GGUF15.7 GBFits82K164K
IQ3_Mukisai/Swift-Qwen3.8-27B-GGUF15.1 GBFits91K182K
Q3_K_Lukisai/Swift-Qwen3.8-27B-GGUF14.3 GBFits102K204K
Q3_K_Mukisai/Swift-Qwen3.8-27B-GGUF13.6 GBFits113K225K
IQ3_XSukisai/Swift-Qwen3.8-27B-GGUF13.0 GBFits122K243K
Q3_K_Sukisai/Swift-Qwen3.8-27B-GGUF13.0 GBFits123K245K
IQ3_XXSukisai/Swift-Qwen3.8-27B-GGUF12.5 GBFits129K256K
Q2_Kukisai/Swift-Qwen3.8-27B-GGUF11.0 GBFits151K256K
IQ2_Mukisai/Swift-Qwen3.8-27B-GGUF10.7 GBFits156K256K
IQ2_Sukisai/Swift-Qwen3.8-27B-GGUF9.90 GBFits168K256K
IQ2_XSukisai/Swift-Qwen3.8-27B-GGUF9.30 GBFits177K256K
IQ2_XXSukisai/Swift-Qwen3.8-27B-GGUF9.09 GBFits180K256K
BF16bartowski/ukisai_Swift-Qwen3.8-27b-GGUF54.7 GBDoesn't fit——
Q8_0bartowski/ukisai_Swift-Qwen3.8-27b-GGUF29.1 GBDoesn't fit——
Q6_K_Lbartowski/ukisai_Swift-Qwen3.8-27b-GGUF25.0 GBDoesn't fit——
Q6_Kbartowski/ukisai_Swift-Qwen3.8-27b-GGUF23.9 GBDoesn't fit——
Q6_K_Sbartowski/ukisai_Swift-Qwen3.8-27b-GGUF22.9 GBDoesn't fit——
Q5_K_Mbartowski/ukisai_Swift-Qwen3.8-27b-GGUF20.9 GBDoesn't fit4K8K
Q5_K_Sbartowski/ukisai_Swift-Qwen3.8-27b-GGUF19.6 GBTight24K48K
Q4_K_Lbartowski/ukisai_Swift-Qwen3.8-27b-GGUF18.8 GBTight35K70K
Q4_1bartowski/ukisai_Swift-Qwen3.8-27b-GGUF17.8 GBTight50K100K
IQ4_NLbartowski/ukisai_Swift-Qwen3.8-27b-GGUF17.4 GBTight56K111K
Q4_K_Mbartowski/ukisai_Swift-Qwen3.8-27b-GGUF17.4 GBTight56K111K
Q4_K_Sbartowski/ukisai_Swift-Qwen3.8-27b-GGUF16.4 GBFits72K144K
Q4_0bartowski/ukisai_Swift-Qwen3.8-27b-GGUF16.3 GBFits72K144K
IQ4_XSbartowski/ukisai_Swift-Qwen3.8-27b-GGUF15.5 GBFits85K170K
IQ3_Mbartowski/ukisai_Swift-Qwen3.8-27b-GGUF14.9 GBFits94K188K
Q3_K_Lbartowski/ukisai_Swift-Qwen3.8-27b-GGUF14.1 GBFits105K210K
Q3_K_Mbartowski/ukisai_Swift-Qwen3.8-27b-GGUF13.4 GBFits116K232K
IQ3_XSbartowski/ukisai_Swift-Qwen3.8-27b-GGUF12.8 GBFits125K250K
Q3_K_Sbartowski/ukisai_Swift-Qwen3.8-27b-GGUF12.7 GBFits126K252K
IQ3_XXSbartowski/ukisai_Swift-Qwen3.8-27b-GGUF12.3 GBFits132K256K
Q2_Kbartowski/ukisai_Swift-Qwen3.8-27b-GGUF10.8 GBFits154K256K
IQ2_Mbartowski/ukisai_Swift-Qwen3.8-27b-GGUF10.5 GBFits159K256K
IQ2_Sbartowski/ukisai_Swift-Qwen3.8-27b-GGUF9.68 GBFits171K256K
IQ2_XSbartowski/ukisai_Swift-Qwen3.8-27b-GGUF9.09 GBFits180K256K
IQ2_XXSbartowski/ukisai_Swift-Qwen3.8-27b-GGUF8.88 GBFits183K256K

Swift-Qwen3.8-27b on other hardware

Popular models that run on Mac with 32 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.