Qwen3.8 Flash Next (125B-A6B) on Apple M3 Ultra (96 GB)

Can the Apple M3 Ultra (96 GB) run Qwen3.8 Flash Next (125B-A6B)?

Yes, it runs well (over GPU memory limit)

Runs well (over GPU memory limit). At Q2_K it needs about 78.6 GB of 72.0 GB usable, with an estimated speed of 116 tok/s.

Best quant: Q2_K
Generation speed: 116 tok/s
Prompt processing: 2,935 tok/s
First token (1K prompt): 0.3 s
Largest safe context: —

Best app to run it on the Apple M3 Ultra (96 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX · use the MLX build

Splits the model between GPU memory and system RAM, which this setup needs.
Point-and-click: search, download and chat in one window.

Open Qwen3.8 Flash Next (125B-A6B) in LM Studio

llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.
Ollama Splits the model between GPU memory and system RAM, which this setup needs.

Want an agent? Qwen3.8 Flash Next (125B-A6B) supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Qwen3.8 Flash Next (125B-A6B)

Recommended for the Apple M3 Ultra (96 GB): Q2_K. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q2_K (UD-Q2_K_XL) files (opens in a new tab)

huggingface.co/unsloth/Qwen3.8-Flash-Next-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Qwen3.8-Flash-Next-GGUF

Original weights · Hugging Face

Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.

huggingface.co/Qwen/Qwen3.8-Flash-Next (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Alibaba. The weights themselves download from Hugging Face.

github.com/QwenLM/Qwen3.8 (opens in a new tab)

Qwen’s current repo: Qwen3.5 and Qwen3.6 redirect here.

git clone https://github.com/QwenLM/Qwen3.8

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs wellover GPU memory limit: How well it runs on the Apple M3 Ultra (96 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	30.4 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	70.4 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Apple M3 Ultra (96 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	78.6 GB	72.0 GB	116 tok/s	Runs wellover GPU memory limit	67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q2_K_XL) · folder (opens in a new tab)
`Q3_K_M`	94.8 GB	72.0 GB	—	Won't run	81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q3_K_XL) · folder (opens in a new tab)
`Q4_K_M`	116 GB	72.0 GB	—	Won't run	91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q5_K_M`	134 GB	72.0 GB	—	Won't run	93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q5_K_XL) · folder (opens in a new tab)
`Q6_K`	154 GB	72.0 GB	—	Won't run	95Excellent quality (A+) · 95 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q6_K_XL) · folder (opens in a new tab)
`Q8_0`	197 GB	72.0 GB	—	Won't run	96Excellent quality (A+) · 96 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 13/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	367 GB	72.0 GB	—	Won't run	96Excellent quality (A+) · 96 of 100: how capable the model is at F16, whatever it runs on. Match score 13/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

93Excellent quality (A+) · 93 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 97/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q5_K_M · 84.1 tok/s · Runs great
96Excellent quality (A+) · 96 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q8_0 · 57.4 tok/s · Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q4_K_M · 95.6 tok/s · Runs great
81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB10 (128 GB) Q3_K_M · 58.5 tok/s · Runs well (tight fit)
81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q3_K_M · 187 tok/s · Runs well (tight fit)
81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) Q3_K_M · 63.1 tok/s · Runs well (tight fit)

Quick answers

How much memory does Qwen3.8 Flash Next (125B-A6B) need on the M3 Ultra 96GB?

At Q2_K it needs about 78.6 GB. The M3 Ultra 96GB has 72.0 GB usable.

How fast is Qwen3.8 Flash Next (125B-A6B) on the M3 Ultra 96GB?

About 116 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Qwen3.8 Flash Next (125B-A6B) should I use on the M3 Ultra 96GB?

Q2_K. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.