Baichuan 2 13B Chat on NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip

Can the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip run Baichuan 2 13B Chat?

Yes, it runs great

Runs great. At F16 it needs about 44.4 GB of 252 GB usable, with an estimated speed of 147 tok/s.

Best quant: F16
Generation speed: 147 tok/s
Prompt processing: 4,144 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 4K

Best app to run it on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

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

Open Baichuan 2 13B Chat 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 Linux

vLLM

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/Baichuan2-13B-Chat

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

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 2 13B Chat

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/mradermacher/Baichuan2-13B-Chat-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/Baichuan2-13B-Chat-i1-GGUF

Original weights · Hugging Face

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

huggingface.co/baichuan-inc/Baichuan2-13B-Chat (opens in a new tab)

No sign-in needed.

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at F16, 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 GB300 Grace Blackwell Ultra Desktop Superchip: 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.	11.7 / 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.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	4.1 / 15
Match score	55.8 / 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 GB300 Grace Blackwell Ultra Desktop Superchip

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	22.1 GB	252 GB	1,030 tok/s	Runs great	18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	23.4 GB	252 GB	811 tok/s	Runs great	21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	25.0 GB	252 GB	627 tok/s	Runs great	24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	26.4 GB	252 GB	518 tok/s	Runs great	25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	28.0 GB	252 GB	435 tok/s	Runs great	25Basic quality (D) · 25 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	31.3 GB	252 GB	319 tok/s	Runs great	26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`F16`	44.4 GB	252 GB	147 tok/s	Runs great	26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 4K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

26Basic quality (D) · 26 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. NVIDIA GeForce RTX 3090 Q8_0 · 42.1 tok/s · Runs great
26Basic quality (D) · 26 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. NVIDIA GeForce RTX 4090 Q8_0 · 45.3 tok/s · Runs great
25Basic quality (D) · 25 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q6_K · 50.7 tok/s · Runs great
26Basic quality (D) · 26 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. NVIDIA GeForce RTX 5090 Q8_0 · 80.6 tok/s · Runs great
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q4_K_M · 48.7 tok/s · Runs great
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q4_K_M · 59.3 tok/s · Runs great

Quick answers

How much memory does Baichuan 2 13B Chat need on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB?

At F16 it needs about 44.4 GB. The NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB has 252 GB usable.

How fast is Baichuan 2 13B Chat on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB?

About 147 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Baichuan 2 13B Chat should I use on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB?

F16. 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.