Can Qwen3.8-Flash-Next run on Mac Studio M3 Ultra 256GB?

YES — Runs great

IQ4_XS · 4K context · formula estimate

What this means

Qwen3.8-Flash-Next fits on the Mac Studio M3 Ultra · 256GB at IQ4_XS. We estimate it uses 107.9GB of the conservative 248GB working budget.

Estimated decode speed is 91–127.5 tokens/s. A roughly 300-word answer may take around 4 seconds.

View technical details ↓Setup guide →

91–127.5tokens/s

estimated · instant

107.9GB

needed at IQ4_XS

IQ4_XS

quant selected

140.1GB

working headroom

needs 107.9 GBworking budget 248 GB

Apple M3 Ultra256 GB unified memory MetalActive cooling

See how fast it feels

Using the midpoint of our 91–127.5 tokens/s estimate for this demo.

Live demo · 109.3 tokens/s

▌

Compare other speeds →

Where the memory goes

Component	Detail	GB
Model weights	IQ4_XS GGUF (93.7 GB) + mmap overhead	98.4
KV cache	4K context window	8.8
Runtime	macOS inference app + compute buffers	0.8
Total needed	at IQ4_XS, 4K context	107.9
Working budget	256 GB unified memory − conservative macOS reserve	248
Headroom	remaining inside the working budget	140.1

Pick your quant

Quant	Download	Memory	Estimated speed	Verdict
IQ1_S	72.5 GB	85.7 GB	~117.7–164.7 tok/s	✓ Runs great
IQ4_XS ★	93.7 GB	107.9 GB	~91–127.5 tok/s	✓ Runs great

Get it running on this Mac

Choose the beginner-friendly build instead.

This Mac has enough memory, but the tracked IQ4_XS ternary file is not supported by the current point-and-click apps. For a first local chat, use Bonsai 27B 1-bit in Locally AI. Do not download PQ2_0; the publisher marks it unsupported.

Only use the publisher tool if you are comfortable with Terminal.

The advanced path is complete below, but it is not required for ordinary local AI.

Advanced publisher setup (Terminal)

Install Apple's command-line tools if macOS asks, then run:

git clone https://github.com/PrismML-Eng/Bonsai-demo.git
cd Bonsai-demo
BONSAI_OPENWEBUI=0 BONSAI_SKIP_MLX=1 BONSAI_FAMILY=undefined BONSAI_MODEL=undefined ./setup.sh
BONSAI_FAMILY=undefined BONSAI_MODEL=undefined BONSAI_CTX=4096 ./scripts/start_llama_server.sh

When the server says it is ready, open http://localhost:8080. Start with 4K context. This route uses the publisher's Prism runtime, not Jan or LM Studio.

Other models on this Mac

LongCat Flash Chat · IQ1_S Ornith 1.0 397B · IQ4_XS Hunyuan 3 (Hy3) · Q4_K_M DeepSeek V4 Flash 0731 · Q4_K_XL Inkling Small · Q4_K_M Ling 3.0 Flash · Q4_K_M

Qwen3.8-Flash-Next on other Mac Studio M3 Ultra configurations

Check 96GB Check 512GB

FAQ

Can the Mac Studio M3 Ultra · 256GB run Qwen3.8-Flash-Next?

Yes at IQ4_XS. We estimate about 107.9GB of working memory and 91–127.5 tokens/s at 4K context.

Which Qwen3.8-Flash-Next quant should I use on this Mac?

IQ4_XS. It is a 93.7GB download and leaves about 140.1GB inside our conservative working budget.

Which app should I use for Qwen3.8-Flash-Next on this Mac?

Current beginner Mac apps do not load this exact file. Use Bonsai 27B 1-bit in Locally AI instead, or open the advanced publisher instructions on this page.

Are these speeds measured on a Mac Studio M3 Ultra?

No. The range is a formula estimate based on memory bandwidth, model size, active parameters, cooling, and a 4K context. The app, backend, thermals, and prompt can change real performance.