Ling Flash 2.0 (100B-A6B) on NVIDIA L40S

Can the NVIDIA L40S run Ling Flash 2.0 (100B-A6B)?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q2_K it needs about 44.7 GB of 48.0 GB usable, with an estimated speed of 151 tok/s.

Best quant: Q2_K
Generation speed: 151 tok/s
Prompt processing: 10,812 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 32K

Best app to run it on the NVIDIA L40S

On Linux

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open Ling Flash 2.0 (100B-A6B) in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open Ling Flash 2.0 (100B-A6B) in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

Want an agent? Ling Flash 2.0 (100B-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 Ling Flash 2.0 (100B-A6B)

Recommended for the NVIDIA L40S: 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 file (opens in a new tab)

huggingface.co/bartowski/inclusionAI_Ling-flash-2.0-GGUF (opens in a new tab)

ollama run hf.co/bartowski/inclusionAI_Ling-flash-2.0-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/inclusionAI/Ling-flash-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 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (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 welltight fit: How well it runs on the NVIDIA L40S: 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.	23.9 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	24.0 / 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	77.9 / 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 NVIDIA L40S

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	44.7 GB	48.0 GB	151 tok/s	Runs welltight fit	53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	54.0 GB	48.0 GB	71.6 tok/s	Runs welloffloads to RAM	63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	66.3 GB	48.0 GB	34.3 tok/s	Runs welloffloads to RAM	72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q5_K_M`	76.6 GB	48.0 GB	—	Won't run	73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q6_K`	87.9 GB	48.0 GB	—	Won't run	75Great quality (A) · 75 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.	GGUF · folder (opens in a new tab)
`Q8_0`	113 GB	48.0 GB	—	Won't run	76Great quality (A) · 76 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.	GGUF · folder (opens in a new tab)
`F16`	209 GB	48.0 GB	—	Won't run	76Great quality (A) · 76 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

76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q8_0 · 55.6 tok/s · Runs great
76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q8_0 · 56.7 tok/s · Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q5_K_M · 146 tok/s · Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) Q5_K_M · 42.5 tok/s · Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB10 (128 GB) Q5_K_M · 39.2 tok/s · Runs great
75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (128 GB) Q6_K · 53.1 tok/s · Runs well (tight fit)

Quick answers

How much memory does Ling Flash 2.0 (100B-A6B) need on the NVIDIA L40S 48GB?

At Q2_K it needs about 44.7 GB. The NVIDIA L40S 48GB has 48.0 GB usable.

How fast is Ling Flash 2.0 (100B-A6B) on the NVIDIA L40S 48GB?

About 151 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Ling Flash 2.0 (100B-A6B) should I use on the NVIDIA L40S 48GB?

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.