Yes: Qwen3.8-Flash-Next runs on 11 of 54 Macs in the LLMCheck index. It needs about 120 GB at a 4K context, 122 GB at 64K. The smallest and cheapest current Mac at 15+ tok/s is the Mac Studio M5 Max 128 GB ($5,099; 47 tok/s community-measured), with the GPU limit raised. Best measured: 59.6 tok/s on an M5 Max (community).
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).
| Mac | Verdict | Build | Speed | Max context | Model page |
|---|---|---|---|---|---|
| MacBook Air | |||||
| MacBook Air M5 16 GB | Doesn't fit | — | — | — | — |
| MacBook Air M5 24 GB | Doesn't fit | — | — | — | — |
| MacBook Air M5 32 GB | Doesn't fit | — | — | — | — |
| MacBook Air M1 8 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M4 16 GB used | Doesn't fit | — | — | — | — |
| MacBook Air M2 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M3 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M1 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M4 24 GB used | Doesn't fit | — | — | — | — |
| MacBook Air M2 24 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M3 24 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Pro | |||||
| MacBook Pro M6 16 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 24 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M6 24 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M6 32 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 48 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Max 64 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 64 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Max 128 GB | Raise GPU limit command ↓ | 4-bit | community47 tok/s | — | M5 Max page |
| MacBook Pro M3 Max 64 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Pro M3 Max 128 GB refurb | Raise GPU limit command ↓ | Q4_K_M | estimated35 tok/s | — | — |
| Mac mini | |||||
| Mac mini M6 16 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 24 GB | Doesn't fit | — | — | — | — |
| Mac mini M6 24 GB | Doesn't fit | — | — | — | — |
| Mac mini M6 32 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 48 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 64 GB | Doesn't fit | — | — | — | — |
| Mac mini M2 Pro 16 GB refurb | Doesn't fit | — | — | — | — |
| Mac mini M4 16 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 24 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 24 GB used | Doesn't fit | — | — | — | — |
| Mac mini M2 Pro 32 GB refurb | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 48 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 64 GB used | Doesn't fit | — | — | — | — |
| iMac | |||||
| iMac M6 16 GB | Doesn't fit | — | — | — | — |
| iMac M6 24 GB | Doesn't fit | — | — | — | — |
| iMac M6 32 GB | Doesn't fit | — | — | — | — |
| Mac Studio | |||||
| Mac Studio M5 Max 36 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Max 48 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Max 64 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Ultra 96 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Max 128 GB | Raise GPU limit command ↓ | 4-bit | community47 tok/s | — | M5 Max page |
| Mac Studio M5 Ultra 256 GB | Runs | IQ4_NL | community57 tok/s | 256K (full) | M5 Ultra page |
| Mac Studio M5 Ultra 512 GB | Runs | IQ4_NL | community57 tok/s | 256K (full) | M5 Ultra page |
| Mac Studio M2 Max 32 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M1 Ultra 64 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M4 Max 64 GB used | Doesn't fit | — | — | — | — |
| Mac Studio M2 Max 64 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M1 Ultra 128 GB refurb | Raise GPU limit command ↓ | Q4_K_M | estimated57 tok/s | — | — |
| Mac Studio M2 Ultra 128 GB refurb | Raise GPU limit command ↓ | Q4_K_M | estimated57 tok/s | — | — |
| Mac Studio M4 Max 128 GB used | Raise GPU limit command ↓ | Q4_K_M | estimated45 tok/s | — | M4 Max page |
| Mac Studio M2 Ultra 192 GB refurb | Runs | Q4_K_M | estimated57 tok/s | 256K (full) | — |
| Mac Studio M3 Ultra 256 GB used | Runs | Q4_K_M | estimated57 tok/s | 256K (full) | M3 Ultra page |
| Mac Studio M3 Ultra 512 GB refurb | Runs | Q4_K_M | estimated57 tok/s | 256K (full) | M3 Ultra page |
Context memory is computed from its config.json (hybrid: full attention on 12 of 48 layers; Gated DeltaNet layers keep a constant state; sparse-attention indexer keys (compressed) not counted): 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.
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 Qwen3.8-Flash-Next needs about 120 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.
sudo sysctl iogpu.wired_limit_mb=114688sudo sysctl iogpu.wired_limit_mb=114688Weights are 125B 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 125B parameters sit in memory although only 6B are read per token. The first row is the catalog’s own figure (about 120 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.
| Build | Weights | RAM at 4K | at 32K | at 64K | Smallest Mac |
|---|---|---|---|---|---|
| As catalogued | — | 120 GB | 121 GB | 122 GB | 256 GB |
| Q2_K | 42.5 GB | 44 GB | 45 GB | 46 GB | 64 GB |
| Q3_K_M | 61.2 GB | 63 GB | 64 GB | 65 GB | 96 GB |
| Q4_K_M | 71.2 GB | 73 GB | 74 GB | 75 GB | 96 GB |
| Q5_K_M | 88.8 GB | 91 GB | 91 GB | 92 GB | 128 GB |
| Q6_K | 102.5 GB | 104 GB | 105 GB | 106 GB | 128 GB |
| Q8_0 | 132.5 GB | 134 GB | 135 GB | 136 GB | 256 GB |
| F16 | 250.0 GB | 252 GB | 253 GB | 254 GB | 512 GB |
Every published (filled square) and community (hollow circle) run the index holds for Qwen3.8-Flash-Next: 0 published, 12 community, each linked to its source. LLMCheck runs no tests of its own. One row is one measurement session; on each chip the table above shows the lower median of the eligible runs (plain decode at 5 bits or fewer), and a binned or “not an anchor” run is shown but never used as a reference.
| Chip | Runtime | Quant | Decode | Context | Date | Source |
|---|---|---|---|---|---|---|
| M5 Ultra | llama.cpp | IQ4_NL | community57 tok/s | — | 2026-10-11 | llamaperf.com |
| M3 Ultra | MLX | 4-bit | community26.5 tok/s | — | 2026-08-31 | huggingface.co not an anchor |
| M3 Ultra | MLX | 4-bit | community25.1 tok/s | short prompt | 2026-09-02 | huggingface.co not an anchor |
| M5 Max | MLX | oQ4e | community69.7 tok/s | 512-token coding answers, median of 5 at T 0.6 | 2026-10-18 | github.com not an anchor |
| M5 Max | MLX | 4-bit | community59.6 tok/s | 512-token coding answer after a short prompt, median of 5 at T 0.6 | 2026-10-25 | github.com |
| M5 Max | MLX | oQ4e | community58.7 tok/s | 4k | 2026-10-24 | omlx.ai |
| M5 Max | MLX | 4-bit | community52.6 tok/s | 512-token coding answer after a short prompt, median of 5 at T 0.6 | 2026-10-25 | github.com |
| M5 Max | Ollama | Q4_K_M | community50.1 tok/s | 512-token coding answers, median of 5 at T 0.6 | 2026-10-18 | github.com |
| M5 Max | MLX | 4-bit | community47 tok/s | coding task (prompt length not stated) | 2026-08-29 | mtplx.com |
| M5 Max | llama.cpp | IQ4_NL | community46.4 tok/s | 512-token coding answers, median of 5 at T 0.6 | 2026-10-18 | github.com |
| M5 Max | MLX | 4-bit | community43.8 tok/s | — | 2026-08-29 | huggingface.co |
| M5 Max | MLX | oQ4e | community28.5 tok/s | 1k | 2026-08-28 | omlx.ai |
The index has no verified Ollama tag for Qwen3.8-Flash-Next. Start from its listing and copy the exact name of a build that fits: Search the Ollama library → · model card →
GGUF builds run in LM Studio or llama.cpp; MLX builds run in LM Studio or mlx-lm.
On the Mac Studio M5 Ultra (256 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is 57 tok/s (community run) at IQ4_NL; keep the context at or under 256K there, or use a q8 KV cache.
Step-by-step: the Ollama install guide.
Mac Studio M5 Max (128 GB) — smallest current Mac that runs it and cheapest at 15+ tok/s, $5,099 new (Apple list price, checked 2026-11-14), 47 tok/s (community run) once the GPU memory limit is raised. Amazon does not stock the Mac Studio M5 Max (128 GB): Apple builds it to order.
Yes. Qwen3.8-Flash-Next needs about 120 GB of unified memory at a short (4K-token) context, so it runs on 11 of the 54 Mac configurations in the LLMCheck index; 5 of them hold it inside macOS’s default GPU memory limit and 6 only after raising that limit. The smallest Mac Apple sells new that runs it is the Mac Studio M5 Max (128 GB).
About 120 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 121 GB in total at 32K and 122 GB at 64K with the default 16-bit cache (about 121 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.
On an M5 Max, the chip the leaderboard quotes it on, the index figure is 47 tok/s (community run) at 4-bit. The best measured figure is 59.6 tok/s on an M5 Max 128 GB (community run, 4-bit). Every Mac’s figure is in the table on this page with its provenance: published, community run or estimated.
Among Macs Apple sells new, the Mac Studio M5 Max (128 GB), $5,099 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Qwen3.8-Flash-Next, at 47 tok/s (community run), after raising the GPU memory limit.
On 6 of the 54 configurations, yes: Mac Studio M5 Max 128 GB, MacBook Pro M5 Max 128 GB, Mac Studio M1 Ultra 128 GB (used) and 3 more. macOS lets the GPU use only part of unified memory by default (about 108 GB on the Mac Studio M5 Max (128 GB)), and Qwen3.8-Flash-Next needs about 120 GB. Running sudo sysctl iogpu.wired_limit_mb=114688 in Terminal raises the limit on a 128 GB Mac until the next restart. From 256 GB up, every Mac Apple sells new holds it inside the default limit.
Q4_K_M (about 71 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 132 GB) is closer to full quality and needs a 256 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 61 and 42 GB at a quality cost. The index’s reference figure (47 tok/s on an M5 Max) is for its 4-bit build.
Its own window is 256K tokens. At macOS’s default GPU limit, the Mac Studio M5 Ultra (256 GB) holds about 256K (the full window).
LLMCheck. (2026). Can I run Qwen3.8-Flash-Next on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/qwen38-flash-next/ (updated ). CC BY 4.0.