OpenModelsHQ

Qwen3-8B

Alibaba QwenLLMDenseApache-2.0China Desk

Qwen3-8B is an open-weight language model from Alibaba Qwen with 8.2B parameters. At 4-bit it needs about 6.7 GB of memory, so the smallest current device that fits it is the Mac mini M6 (16GB).

Overview

Estimated memory at 4-bit
6.7GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
8.2B
Dense
Context window
40K
40,960 tokens
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
Alibaba Qwen
Released
27 Apr 2025
Parameters
8.2B
Type
Language
Context
40,960 tokens
License
Apache-2.0
HF downloads, 30 days
6,165,334
Repository
Qwen/Qwen3-8B
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
Qwen3-8B needs about 6.7 GB at 4-bit, 10.9 GB at 8-bit and 19.3 GB at 16-bit. At 4-bit it fits GeForce RTX 5060 Ti 16GB, GeForce RTX 5090, DGX Spark, Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q46.7 GB
Q810.9 GB
BF1619.3 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 6.7 GBFits 19%Mac mini M6 (16GB)16 GB memory
8-bit (Q8)≈ 10.9 GBFits 30%GeForce RTX 5060 Ti 16GB16 GB memory
16-bit (BF16)≈ 19.3 GBFits 54%Arc Pro B6024 GB memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

No trusted MLX build found yet.

Check your Mac

With GGUF

Choose a file for llama.cpp or a compatible app.

unsloth/Qwen3-8B-GGUFFind compatible hardware

Through an API

No hosted API found.

GGUF with llama.cppView repository
llama-cli -hf unsloth/Qwen3-8B-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of llama.cpp. We have not run them; check each repository for available files.

More about this model

Frequently asked questions

How much memory does Qwen3-8B need? At an 8k context, about 6.7 GB at 4-bit, 10.9 GB at 8-bit and 19.3 GB at 16-bit (BF16). A longer context needs more.

Can I run Qwen3-8B on a Mac? The smallest current Mac that fits the 4-bit estimate of 6.7 GB is the Mac mini M6 (16GB). We have not found a trusted MLX build yet, but a GGUF build is available.

Does the full context fit? Qwen3-8B supports up to 40,960 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

Apache-2.0. This license permits commercial use, modification and redistribution, with conditions such as keeping the required notices. This summary is not legal advice.

Read Apache-2.0

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card, GGUF repository.