Ling Mini 2.0 (16B-A1.4B) on Apple M1 Pro (32 GB)

Can the Apple M1 Pro (32 GB) run Ling Mini 2.0 (16B-A1.4B)?

Yes, it runs great

Runs great. At Q6_K it needs about 16.0 GB of 21.4 GB usable, with an estimated speed of 76.0 tok/s.

Best quant: Q6_K
Generation speed: 76.0 tok/s
Prompt processing: 2,303 tok/s
First token (1K prompt): 0.4 s
Largest safe context: 32K

Best app to run it on the Apple M1 Pro (32 GB)

On macOS

LM Studio

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

Runs the MLX build, typically 35–90% faster than GGUF for a model with 1.4B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open Ling Mini 2.0 (16B-A1.4B) in LM Studio

MLX LM Runs the MLX build, typically 35–90% faster than GGUF for a model with 1.4B active parameters on Apple silicon.
Unsloth Desktop Runs the MLX build, typically 35–90% faster than GGUF for a model with 1.4B active parameters on Apple silicon.

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 Mini 2.0 (16B-A1.4B)

Recommended for the Apple M1 Pro (32 GB): Q6_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 Q6_K file (opens in a new tab)

huggingface.co/inclusionAI/Ling-mini-2.0-GGUF (opens in a new tab)

ollama run hf.co/inclusionAI/Ling-mini-2.0-GGUF:Q6_K

Original weights · Hugging Face

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

huggingface.co/inclusionAI/Ling-mini-2.0 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Ant Group (inclusionAI). The weights themselves download from Hugging Face.

github.com/inclusionAI/Ling-V2 (opens in a new tab)

git clone https://github.com/inclusionAI/Ling-V2

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

How it’s rated

Quality 51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q6_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 great: How well it runs on the Apple M1 Pro (32 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.	23.2 / 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.	25.0 / 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	78.2 / 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 M1 Pro (32 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	9.2 GB	21.4 GB	140 tok/s	Runs great	36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	10.6 GB	21.4 GB	120 tok/s	Runs great	43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	12.6 GB	21.4 GB	100 tok/s	Runs great	49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	14.2 GB	21.4 GB	86.8 tok/s	Runs great	50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	16.0 GB	21.4 GB	76.0 tok/s	Runs great	51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	19.9 GB	21.4 GB	59.5 tok/s	Runs welltight fit	52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	35.2 GB	21.4 GB	—	Won't run	52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (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

52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q8_0 · 154 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) F16 · 54.1 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) F16 · 68.0 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8_0 · 161 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 166 tok/s · Runs great
50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q5_K_M · 167 tok/s · Runs great

Quick answers

How much memory does Ling Mini 2.0 (16B-A1.4B) need on the M1 Pro 32GB?

At Q6_K it needs about 16.0 GB. The M1 Pro 32GB has 21.4 GB usable.

How fast is Ling Mini 2.0 (16B-A1.4B) on the M1 Pro 32GB?

About 76.0 tok/s at Q6_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Ling Mini 2.0 (16B-A1.4B) should I use on the M1 Pro 32GB?

Q6_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.