Ling Mini 2.0 (16B-A1.4B) on AMD EPYC 7002 / 7003 series NAS (512 GB)

Can the AMD EPYC 7002 / 7003 series NAS (512 GB) run Ling Mini 2.0 (16B-A1.4B)?

Yes, it runs great

Runs great. At Q8_0 it needs about 55.9 GB of 471 GB usable, with an estimated speed of 42.6 tok/s.

Best quant: Q8_0
Generation speed: 42.6 tok/s
Prompt processing: 286 tok/s
First token (1K prompt): 3.6 s
Largest safe context: 32K

Best app to run it on the AMD EPYC 7002 / 7003 series NAS (512 GB)

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

Usually the first to support new model architectures.

llama-server -hf inclusionAI/Ling-mini-2.0-GGUF:Q8_0

Ollama Runs the Hugging Face GGUF with ollama run hf.co/…
KoboldCpp

How we choose: the files published for this model, which apps run in a container on a NAS without a graphics card (models run on its processor), and whether the model fits fully in the memory models can use. Details.

Download Ling Mini 2.0 (16B-A1.4B)

Recommended for the AMD EPYC 7002 / 7003 series NAS (512 GB): Q8_0. 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 Q8_0 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:Q8_0

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 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8_0, 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 AMD EPYC 7002 / 7003 series NAS (512 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.	23.4 / 45
Memory fitFull marks when the model fits in the share of the NAS’s memory that models can use (the rest stays with the NAS system and its storage services); 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.	2.7 / 15
Match score	66.1 / 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 AMD EPYC 7002 / 7003 series NAS (512 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	45.1 GB	471 GB	108 tok/s	Runs great	36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	46.6 GB	471 GB	91.0 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 61/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	48.5 GB	471 GB	74.7 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 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	50.2 GB	471 GB	64.0 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 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	52.0 GB	471 GB	55.4 tok/s	Runs great	51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	55.9 GB	471 GB	42.6 tok/s	Runs great	52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	71.1 GB	471 GB	21.2 tok/s	Runs well	52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (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

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.