← All models

Model

Qwen3.5 (4B and 9B)

Made by Alibaba Qwen · License: Apache 2.0

A free model for chat, code, questions about images and long documents. You start it with one command.

Will it run on my computer?

Mac

16 GBFits24 GBFits32 GBFits36 GBFits48 GBFits64 GBFits96 GBFits128 GBFits192 GBFits256 GBFits512 GBFits

NVIDIA graphics card

8 GBFitssmaller version12 GBFits16 GBFits24 GBFits32 GBFitsTwo 24 GB cardsFits

AMD Ryzen AI Max

64 GBFits128 GBFits

This is our estimate from the download size. We did not test it on each computer. “Smaller version” means a smaller download than the command below. Tap your computer to see the exact command.

Start it

  1. Install Ollama from ollama.com/download.
  2. Open Terminal.
  3. Paste this command:
ollama run qwen3.5:9b-q4_K_M

What happens next

If it breaks

  1. It forgets the start of a long chat, or ignores most of a document you pasted.

    Ollama does not use the model's full memory by default. Its docs say it starts at 4K tokens on graphics cards under 24 GB and 32K on 24-48 GB. When a chat runs past that, the oldest messages are dropped without any warning.

    Raise the context length with the slider in the Ollama app's Settings, or type this in a Terminal chat. It uses more memory, so check the result with ollama ps (the CONTEXT column).

    /set parameter num_ctx 32768

    Source: 1 · 2

  2. Replies crawl out a word at a time.

    The model did not fit in graphics memory, so Ollama quietly ran part of it on the CPU. Speed drops a lot, but you get no error.

    Run ollama ps while the model runs. Look at the PROCESSOR column. If it does not say 100% GPU, free some memory. Close other models with ollama stop <name>, lower the context length, or pick a smaller version.

    ollama ps

    Source: 1 · 2

Sizes and versions

Will it run on my computer?

For qwen3.5:9b-q4_K_M (6.6 GB download; 6,550,825,373 bytes in the Ollama registry). Context up to 256K, but Ollama starts much lower, see below.

8 GB graphics cardWon't fitTry qwen3.5:4b (3.3 GB): Fits
16 GB graphics cardFits
24 GB graphics cardFits
32 GB graphics cardFits
16 GB MacFits
24 GB MacFits
32 GB MacFits
64 GB+ MacFits
AMD Ryzen AI Max+ PC, 128 GB (graphics memory set to 96 GB)Fits
  • This is our estimate from published download sizes. We did not test these ourselves.
  • Fits = download x 1.25 + 2 GB fits in usable memory. That leaves room for longer chats.
  • Tight = only download + 1.5 GB fits. Short chats work, but long chats or documents may spill onto the CPU and slow down.
  • Usable memory on a graphics card is all of its graphics memory.
  • On a Mac it is 2/3 of memory up to 32 GB and 3/4 at 64 GB+. By default macOS keeps part of memory away from the GPU. Apple says a 32 GB Mac gives the GPU 21 GB and a 64 GB Mac 48 GB.
  • On an AMD Ryzen AI Max+ PC with 128 GB, it is the graphics memory you set in AMD Software. AMD says you can set up to 96 GB.
  • Apple · AMD

Sizes checked 2026-10-19.

START HERE Easy: Ollama

INSTALLOllama. ollama.com/download
RUN
ollama run qwen3.5:9b-q4_K_M
SIZE6.6 GB download
NEEDSA Mac with 16 GB of memory or a 12 GB graphics card. On an 8 GB graphics card, use ollama run qwen3.5:4b (3.3 GB) instead.
SOURCEsource · checked 2026-10-19

Recommended quants

  • Ollama qwen3.5:4b = 4b-q4_K_M (3.3 GB; 3,324,173,757 bytes)
    https://ollama.com/library/qwen3.5/tags
    Same file as the 4b-q4_K_M tag. Includes the picture reader (676 MB).
  • Ollama qwen3.5:9b-q4_K_M = 9b (6.6 GB; 6,550,825,373 bytes)
    https://ollama.com/library/qwen3.5/tags
    Same file as the 9b tag. Includes the picture reader (922 MB).
Scores and how it compares

Independent score: Artificial Analysis Intelligence Index 11 (9B (Reasoning)), checked 2026-10-19 · source.

Checked 2026-10-19. AA measured the 9B (Reasoning) version at 11. AA lists the 4B (Reasoning) version at 13, but marks that score as an estimate. Ollama runs these models with thinking on.

Arena: not on the Arena boards we use (checked 2026-10-19).

Pick this if your computer has little memory. The 4B version reads pictures well on an 8 GB graphics card. The 9B version handles long documents on a 16 GB Mac.

Skip this if your computer can run Gemma 4 or Qwen3.8 27B. Those have higher independent scores.

Compare: Gemma 4 (26B-A4B / 31B) · Qwen3.8-27B · Pick your computer

BEST PICK ONMac 16, 24, 32, 36 GB · NVIDIA 8, 12, 16, 24 GB (at least one job)
Settings and apps

Chat template Works

Ollama lists vision, tools and thinking for this model.

Fix:

Sampling settings

Runtimes

OllamaWorksTags qwen3.5:4b (3.3 GB) and qwen3.5:9b-q4_K_M (6.6 GB) as of Oct 19. Mac tags 4b-mlx (4.0 GB) and 9b-mlx (8.9 GB) exist; we do not list them yet.
Sources
MADE BYAlibaba Qwen
LICENSEApache 2.0 · model page · checked 2026-10-19
RELEASED2026-03 (HF repos created Feb 27)
CHECKED2026-10-19 · 6 sources

Small models from Alibaba Qwen that read text and pictures. The 4B version (3.3 GB) suits an 8 GB graphics card. The 9B version (6.6 GB) suits a 16 GB Mac and long documents.

Known issues

Sources checked

Spotted something wrong or a new fix? Email corrections to [email protected]. Corrections are reviewed before publishing.