Skip to content
Local AI Wizard
Your machine
Theme

Qwen3.8 family: which size to run

2 sizes, 27B–2.4T parameters · Alibaba

Checked

Sizes

Qwen3.8 sizes
ModelArchitecture
Qwen3.8 27BAlibaba · Apache 2.0 · Aug 14, 202627BDense262,14475.3292316.5†16.1
Qwen3.8 MaxAlibaba · Qwen3.8 Max · Aug 12, 20262.4TMoE · 95B active262,14478.51,8081,802No GGUF Q4_K_M file (plain or UD-) in the repository collectedNo MLX repository collected

Each size is its own model, with its own scores and memory needs. Q4 estimates are planning figures, not measurements; file sizes are published. The Mac or PC column is for a 32 GB or larger machine (8 GB reserve); machines under 32 GB reserve 25% of their memory (2 to 8 GB), so they need less. The publisher lists 27B, 2.4T-A95B.

† Unsloth's dynamic UD-Q4_K_M file, shown when the repository has no plain Q4_K_M file (the same rule as the model pages); the cell's title names the file.

How to read this table

Q4 means compressed to about 4 bits per weight. GGUF (llama.cpp, Ollama, LM Studio) and MLX (Apple silicon) are file formats; the sizes shown are the published 4-bit files. A dash means no value is published or collected for that size; the reason is in the cell's accessible text.

Which size fits my machine

The largest size whose Q4 planning estimate fits what each machine offers. A planning estimate, not a measurement and not a speed. Smaller machines are left out; the largest one that fits no size is kept to show the limit.

Largest Qwen3.8 size per machine
MachineLargest Qwen3.8 size with enough memory
Mac mini M4 · 24 GB unified24No size of this family has a Q4 estimate within what this machine offersNo size fits, so there is no estimate to compare
Mac mini M4 · 32 GB unified32Qwen3.8 27B29
Mac mini M5 Pro · 64 GB unified56Qwen3.8 27B29
Mac Studio M5 Max · 128 GB unified104Qwen3.8 27B29
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unified392Qwen3.8 27B29
RTX 5080 · 16 GB VRAM16No size of this family has a Q4 estimate within what this machine offersNo size fits, so there is no estimate to compare
RTX 4090 · 24 GB VRAM24Qwen3.8 27B23
RTX 5090 · 32 GB VRAM32Qwen3.8 27B23
DGX H100 · 8 × 80 GB640Qwen3.8 27B37

A dash means no size of this family fits that machine. The requirement is the size's Q4 estimate with that machine's own reserve: a graphics card reserves 2 GB, as in the sizes table; a Mac or PC reserves 25% of its memory (2 to 8 GB), so below 32 GB its figure is lower than the sizes table's. A server profile reserves 2 GB per graphics card, so its figure is higher.

Smallest machine for each size

The profile with the least memory that still has enough for the size's Q4 estimate, from the hardware catalog.

Smallest machine per Qwen3.8 size
SizeSmallest Mac or PC-memory profileSmallest graphics-card profileServer-class profile
Qwen3.8 27BMac mini 2024 · M4 · 32 GBRTX 3090 · 24 GBDGX H100 · 8 × 80 GB · 640 GB
Qwen3.8 MaxNo Mac, laptop or PC profile in the catalog has enough memory for this sizeNo graphics-card profile in the catalog has enough memory for this sizeEven the largest profile in the catalog (DGX H100 · 8 × 80 GB, 640 GB aggregated) is below this planning estimate

A dash means no profile of that kind in the catalog has enough memory for the size.

Memory by file precision

The same planning formula at three precisions (0.625, 1.125 and 2 bytes per parameter, plus working room and the system reserve). Estimates, not measurements.

Qwen3.8 memory estimate by precision
Size
Qwen3.8 27B292345397367
Qwen3.8 Max1,8081,8023,2483,2425,7685,762

Family tree

Family, sizes and, for each size, the two 4-bit files the tables use (GGUF Q4_K_M and MLX 4-bit) when one was collected. Other precisions are not drawn here.

Qwen3.8 family: sizes and published filesSwipe sideways to see the files, or read the list below.
Qwen3.8 family: sizes and published filesFamilySizesFilesQwen3.8Alibaba27BGGUF UD-Q4_K_M16.5 GBMLX 4-bit16.1 GBMax 2.4T A95B95B activeNo Q4_K_M or 4-bit file collected

The same tree as a list:

  • Qwen3.8 · Alibaba
    • 27B
      • GGUF UD-Q4_K_M · 16.5 GB · unsloth/Qwen3.8-27B-GGUF, read Oct 23, 2026
      • MLX 4-bit · 16.1 GB · lmstudio-community/Qwen3.8-27B-MLX-4bit, read Oct 23, 2026
    • Max 2.4T A95B · 95B active
      • No Q4_K_M or 4-bit file collected

Learn more

Sources

Where the family and its sizes are named, and where each number comes from.