on

Can the Apple M3 Max (96 GB) run Ling 2.6 Flash (104B-A7.4B)?

76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well (tight fit)

Runs well (tight fit). At Q4_K_M it needs about 72.0 GB of 72.0 GB usable, with an estimated speed of 37.5 tok/s.

Best quant
Q4_K_M
Generation speed
37.5 tok/s
Prompt processing
1,031 tok/s
First token (1K prompt)
1.0 s
Largest safe context
15K

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

On macOS

LM Studio

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

  • Runs the MLX build, typically 20–35% faster than GGUF for a model with 7.4B active parameters on Apple silicon.
  • Point-and-click: search, download and chat in one window.

Open Ling 2.6 Flash (104B-A7.4B) in LM Studio

  • MLX LM Runs the MLX build, typically 20–35% faster than GGUF for a model with 7.4B active parameters on Apple silicon.
  • Jan Runs the MLX build, typically 20–35% faster than GGUF for a model with 7.4B active parameters on Apple silicon.

Want an agent? Ling 2.6 Flash (104B-A7.4B) 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 Ling 2.6 Flash (104B-A7.4B)

Original weights · Hugging Face

Full-precision files from Ant Group (inclusionAI), for fine-tuning, vLLM, Transformers.

huggingface.co/inclusionAI/Ling-2.6-flash (opens in a new tab)

No sign-in needed.

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q4_K_M, 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 welltight fit
How well it runs on the Apple M3 Max (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.34.2 / 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.24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.14.5 / 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 score87.7 / 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 Max (96 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 49.4 GB 72.0 GB 57.7 tok/s Runs great 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q3_K_M 59.1 GB 72.0 GB 47.0 tok/s Runs great 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q4_K_M 72.0 GB 72.0 GB 37.5 tok/s Runs welltight fit 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q5_K_M 82.7 GB 72.0 GB 26.8 tok/s Slowfar over GPU memory limit 77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q6_K 94.5 GB 72.0 GB — Won't run 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q8_0 120 GB 72.0 GB — Won't run 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
F16 221 GB 72.0 GB — Won't run 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. 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

Quick answers

How much memory does Ling 2.6 Flash (104B-A7.4B) need on the M3 Max 96GB?

At Q4_K_M it needs about 72.0 GB. The M3 Max 96GB has 72.0 GB usable.

How fast is Ling 2.6 Flash (104B-A7.4B) on the M3 Max 96GB?

About 37.5 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Ling 2.6 Flash (104B-A7.4B) should I use on the M3 Max 96GB?

Q4_K_M. 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.

Was this page helpful?