Can the NVIDIA L40 run Baichuan M2 32B?

Yes, it runs great

Runs great. At Q4_K_M it needs about 25.1 GB of 48.0 GB usable, with an estimated speed of 32.4 tok/s.

Best quant: Q4_K_M
Generation speed: 32.4 tok/s
Prompt processing: 1,989 tok/s
First token (1K prompt): 0.5 s
Largest safe context: 93K

Best app to run it on the NVIDIA L40

On Linux

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

vllm serve baichuan-inc/Baichuan-M2-32B

LM Studio Point-and-click: search, download and chat in one window.
SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

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

Open Baichuan M2 32B in LM Studio

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

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 Baichuan M2 32B

Recommended for the NVIDIA L40: Q4_K_M. 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 Q4_K_M file (opens in a new tab)

huggingface.co/bartowski/baichuan-inc_Baichuan-M2-32B-GGUF (opens in a new tab)

ollama run hf.co/bartowski/baichuan-inc_Baichuan-M2-32B-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/baichuan-inc/Baichuan-M2-32B (opens in a new tab)

No sign-in needed.

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

How it’s rated

Quality 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (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 great: How well it runs on the NVIDIA L40: 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.	29.9 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	13.5 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	12.1 / 15
Match score	80.5 / 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 L40

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	18.3 GB	48.0 GB	53.2 tok/s	Runs great	49Fair quality (C) · 49 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 (opens in a new tab)
`Q3_K_M`	21.2 GB	48.0 GB	41.9 tok/s	Runs great	58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	25.1 GB	48.0 GB	32.4 tok/s	Runs great	66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	28.4 GB	48.0 GB	26.7 tok/s	Runs well	67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	32.0 GB	48.0 GB	22.5 tok/s	Runs well	69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	39.9 GB	48.0 GB	16.5 tok/s	Runs well	70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	70.7 GB	48.0 GB	—	Won't run	70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 9/100 (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

69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 46.6 tok/s · Runs well (tight fit)
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4_K_M · 37.8 tok/s · Runs well (tight fit)
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q4_K_M · 35.1 tok/s · Runs well (tight fit)
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 31.0 tok/s · Runs well (tight fit)
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q6_K · 46.6 tok/s · Runs great
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q4_K_M · 17.6 tok/s · Runs well

Quick answers

How much memory does Baichuan M2 32B need on the NVIDIA L40 48GB?

At Q4_K_M it needs about 25.1 GB. The NVIDIA L40 48GB has 48.0 GB usable.

How fast is Baichuan M2 32B on the NVIDIA L40 48GB?

About 32.4 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Baichuan M2 32B should I use on the NVIDIA L40 48GB?

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.