Can I run Qwen3-Coder-Next on a Mac?

Yes: Qwen3-Coder-Next runs on 21 of the 54 Macs in the LLMCheck index. It needs about 48 GB of unified memory at a 4K context and about 50 GB at 64K. The smallest and cheapest current Mac that runs it at 15+ tok/s is the Mac mini M5 Pro 64 GB ($2,699; ~49 tok/s est.). No measured run yet.

RAM at 4K
48
GB
RAM at 64K
50
GB, 16-bit KV
Macs that run it
21
of 54 configs
Best measured
—
no measured run

Qwen3-Coder-Next on every Mac

One row per Mac configuration, grouped by product line. The build is the one each speed is for; the context column is the longest prompt that fits inside macOS’s default GPU memory limit with a 16-bit KV cache (“raised” where the limit has to be raised first; “full” when the whole window fits). Speeds are decode tok/s from the LLMCheck index, each with its provenance mark. For large mixture-of-experts models (over 40B total), the formula’s typical error is about 34% (the median gap to 70 measured plain-decode runs; it tends to undershoot (median −33%), and an estimate scaled from the model’s own measured run is usually closer; method).

Runs fits macOS’s default GPU limit, 15+ tok/sRuns, slowly fits, under 15 tok/sRaise GPU limit fits once the limit is raised (command below)Over GPU limit fits RAM on paper, but even a safe raise is shortDoesn't fit needs more memory than the Mac has
MacVerdictBuildSpeedMax contextModel page
MacBook Air
MacBook Air M5 16 GBDoesn't fit————
MacBook Air M5 24 GBDoesn't fit————
MacBook Air M5 32 GBDoesn't fit————
MacBook Air M1 8 GB refurbDoesn't fit————
MacBook Air M4 16 GB usedDoesn't fit————
MacBook Air M2 16 GB refurbDoesn't fit————
MacBook Air M3 16 GB refurbDoesn't fit————
MacBook Air M1 16 GB refurbDoesn't fit————
MacBook Air M4 24 GB usedDoesn't fit————
MacBook Air M2 24 GB refurbDoesn't fit————
MacBook Air M3 24 GB refurbDoesn't fit————
MacBook Pro
MacBook Pro M6 16 GBDoesn't fit————
MacBook Pro M5 Pro 24 GBDoesn't fit————
MacBook Pro M6 24 GBDoesn't fit————
MacBook Pro M6 32 GBDoesn't fit————
MacBook Pro M5 Pro 48 GBOver GPU limit why ↓Q4_K_Mestimated49 tok/s——
MacBook Pro M5 Max 64 GBRunsQ4_K_Mestimated84 tok/s156KM5 Max page
MacBook Pro M5 Pro 64 GBRunsQ4_K_Mestimated49 tok/s156K—
MacBook Pro M5 Max 128 GBRunsQ4_K_Mestimated84 tok/s256K (full)M5 Max page
MacBook Pro M3 Max 64 GB refurbRunsQ4_K_Mestimated61 tok/s4K—
MacBook Pro M3 Max 128 GB refurbRunsQ4_K_Mestimated61 tok/s256K (full)—
Mac mini
Mac mini M6 16 GBDoesn't fit————
Mac mini M5 Pro 24 GBDoesn't fit————
Mac mini M6 24 GBDoesn't fit————
Mac mini M6 32 GBDoesn't fit————
Mac mini M5 Pro 48 GBOver GPU limit why ↓Q4_K_Mestimated49 tok/s——
Mac mini M5 Pro 64 GBRunsQ4_K_Mestimated49 tok/s156K—
Mac mini M2 Pro 16 GB refurbDoesn't fit————
Mac mini M4 16 GB usedDoesn't fit————
Mac mini M4 Pro 24 GB usedDoesn't fit————
Mac mini M4 24 GB usedDoesn't fit————
Mac mini M2 Pro 32 GB refurbDoesn't fit————
Mac mini M4 Pro 48 GB usedOver GPU limit why ↓Q4_K_Mestimated44 tok/s——
Mac mini M4 Pro 64 GB usedRunsQ4_K_Mestimated44 tok/s4K—
iMac
iMac M6 16 GBDoesn't fit————
iMac M6 24 GBDoesn't fit————
iMac M6 32 GBDoesn't fit————
Mac Studio
Mac Studio M5 Max 36 GBDoesn't fit————
Mac Studio M5 Max 48 GBOver GPU limit why ↓Q4_K_Mestimated84 tok/s—M5 Max page
Mac Studio M5 Max 64 GBRunsQ4_K_Mestimated84 tok/s156KM5 Max page
Mac Studio M5 Ultra 96 GBRunsQ4_K_Mestimated130 tok/s256K (full)M5 Ultra page
Mac Studio M5 Max 128 GBRunsQ4_K_Mestimated84 tok/s256K (full)M5 Max page
Mac Studio M5 Ultra 256 GBRunsQ4_K_Mestimated130 tok/s256K (full)M5 Ultra page
Mac Studio M5 Ultra 512 GBRunsQ4_K_Mestimated130 tok/s256K (full)M5 Ultra page
Mac Studio M2 Max 32 GB refurbDoesn't fit————
Mac Studio M1 Ultra 64 GB refurbRunsQ4_K_Mestimated100 tok/s4K—
Mac Studio M4 Max 64 GB usedRunsQ4_K_Mestimated77 tok/s4K—
Mac Studio M2 Max 64 GB refurbRunsQ4_K_Mestimated61 tok/s4K—
Mac Studio M1 Ultra 128 GB refurbRunsQ4_K_Mestimated100 tok/s256K (full)—
Mac Studio M2 Ultra 128 GB refurbRunsQ4_K_Mestimated100 tok/s256K (full)—
Mac Studio M4 Max 128 GB usedRunsQ4_K_Mestimated77 tok/s256K (full)—
Mac Studio M2 Ultra 192 GB refurbRunsQ4_K_Mestimated100 tok/s256K (full)—
Mac Studio M3 Ultra 256 GB usedRunsQ4_K_Mestimated102 tok/s256K (full)—
Mac Studio M3 Ultra 512 GB refurbRunsQ4_K_Mestimated102 tok/s256K (full)—
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Context memory is computed from its config.json (hybrid: full attention on 12 of 48 layers; Gated DeltaNet layers keep a constant state): about 1.6 GB of 16-bit KV cache at 64K tokens. A q8 cache (llama.cpp -ctk q8_0 -ctv q8_0, Ollama OLLAMA_KV_CACHE_TYPE=q8_0) halves that part. Runtimes also grow a compute buffer with context, so a fit within about 1 GB of the limit is optimistic.

Raising the GPU memory limit

macOS lets the GPU wire only part of unified memory by default (Metal’s recommended working set; M5 and M6 Macs run macOS 26 or later, whose default is higher), and Qwen3-Coder-Next needs about 48 GB. On the Macs marked Raise GPU limit it fits in RAM but not inside that default. The default is a performance threshold, not a hard wall: past it, the runtime moves part of it to the CPU or shortens the context (llama.cpp, Ollama), runs it slowly (MLX), or stops with an out-of-memory error. One command raises the limit until the next restart (sudo sysctl iogpu.wired_limit_mb=0 restores the default sooner); it leaves macOS a reserve, and other apps get less memory while the model is loaded. On the Macs marked Over GPU limit even that raise falls short: the model fits the Mac’s RAM on paper, but a smaller quant or a bigger Mac is the realistic route.

Qwen3-Coder-Next: memory by quantization

Weights are 80B parameters at each format’s effective size (the index’s GB-per-billion table), plus about 2 GB for the runtime and a short context; longer contexts add the KV cache computed from the model’s config.json at 16 bits. It is a mixture-of-experts model: all 80B parameters sit in memory although only 3B are read per token. The first row is the catalog’s own figure (about 48 GB at a 4K context), the one every verdict on this page uses. “Smallest Mac” is the smallest memory size among the Macs Apple sells new that holds it at a 4K context inside that Mac’s default GPU limit. Estimates, not measurements.

BuildWeightsRAM at 4Kat 32Kat 64KSmallest Mac
As catalogued—48 GB49 GB50 GB64 GB
Q2_K27.2 GB29 GB30 GB31 GB48 GB (36 GB with a raised limit)
Q3_K_M39.2 GB41 GB42 GB43 GB64 GB (48 GB with a raised limit)
Q4_K_M45.6 GB48 GB48 GB49 GB64 GB
Q5_K_M56.8 GB59 GB60 GB60 GB96 GB
Q6_K65.6 GB68 GB68 GB69 GB96 GB
Q8_084.8 GB87 GB88 GB88 GB128 GB
F16160.0 GB162 GB163 GB164 GB256 GB

Measured runs

The index holds no published or community run of Qwen3-Coder-Next yet, so every speed on this page is an estimate from the memory-bandwidth model. LLMCheck runs no tests of its own: if you have run it on a Mac, submit the figure with its setup →

Recommended setup

The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 52 GB):

ollama run qwen3-coder-next

Prefer a window to a terminal? LM Studio downloads the same model with one click. · model card →

On the Mac mini M5 Pro (64 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~49 tok/s (estimated) at Q4_K_M; keep the context at or under 156K there, or use a q8 KV cache. The qwen3-coder-next file fits there.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Qwen3-Coder-Next

Mac mini M5 Pro (64 GB) — smallest current Mac that runs it and cheapest at 15+ tok/s, $2,699 new (Apple list price, checked 2026-11-14), ~49 tok/s (estimated). Amazon does not stock the Mac mini M5 Pro (64 GB): Apple builds it to order.

FAQ: Qwen3-Coder-Next on a Mac

Can I run Qwen3-Coder-Next on a Mac?

Yes. Qwen3-Coder-Next needs about 48 GB of unified memory at a short (4K-token) context, so it runs on 21 of the 54 Mac configurations in the LLMCheck index. On 4 more it fits the RAM, but not even a safely raised GPU limit. The smallest Mac Apple sells new that runs it is the Mac mini M5 Pro (64 GB).

How much RAM does Qwen3-Coder-Next need?

About 48 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 49 GB in total at 32K and 50 GB at 64K with the default 16-bit cache (about 49 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does Qwen3-Coder-Next run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is ~84 tok/s (estimated) at Q4_K_M. No published or community run is in the index yet; every speed is an estimate from the memory-bandwidth model. Every Mac’s figure is in the table on this page with its provenance: published, community run or estimated.

What is the cheapest Mac that runs Qwen3-Coder-Next well?

Among Macs Apple sells new, the Mac mini M5 Pro (64 GB), $2,699 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Qwen3-Coder-Next, at ~49 tok/s (estimated).

Do I need to raise the GPU memory limit to run Qwen3-Coder-Next?

On Mac mini M5 Pro 48 GB, Mac Studio M5 Max 48 GB, MacBook Pro M5 Pro 48 GB and 1 more even a safely raised limit is short: expect heavy swapping, a CPU split or an out-of-memory error. From 64 GB up, every Mac Apple sells new holds it inside the default limit.

Which quantization of Qwen3-Coder-Next should I use?

Q4_K_M (about 46 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 85 GB) is closer to full quality and needs a 128 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 39 and 27 GB at a quality cost. The index’s reference figure (84 tok/s on an M5 Max) is for its Q4_K_M build.

How much context can Qwen3-Coder-Next use on a Mac?

Its own window is 256K tokens. At macOS’s default GPU limit, the Mac mini M5 Pro (64 GB) holds about 156K. The full window needs about 55 GB, which a 96 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.

Cite this page

LLMCheck. (2026). Can I run Qwen3-Coder-Next on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/qwen3-coder-next/ (updated ). CC BY 4.0.

How to cite LLMCheck →Data: CC BY 4.0Markdown version

Related

Figures from the LLMCheck index, data version 2026-11-18. Verdicts and context limits are estimates from each model’s catalog memory figure and config.json.