on

Can the NVIDIA GB10 (64 GB) run LLaVA 1.5 13B?

15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At Q2_K it needs about 13.9 GB of 57.6 GB usable, with an estimated speed of 41.2 tok/s.

Best quant
Q2_K
Generation speed
41.2 tok/s
Prompt processing
1,672 tok/s
First token (1K prompt)
0.6 s
Largest safe context
4K

Best app to run it on the NVIDIA GB10 (64 GB)

On Linux

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

  • One command with Ollama’s own build of this model.
  • Serves an OpenAI-compatible API that other apps and coding tools can use.
ollama run llava:13b-v1.5-q2_K
  • 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.
  • 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.

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 LLaVA 1.5 13B

Recommended for the NVIDIA GB10 (64 GB): Q2_K. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run llava:13b-v1.5-q2_K

Original weights · Hugging Face

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

huggingface.co/liuhaotian/llava-v1.5-13b (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (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 great
How well it runs on the NVIDIA GB10 (64 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.6.9 / 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.5.6 / 15
Match score52.5 / 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 GB10 (64 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 13.9 GB 57.6 GB 41.2 tok/s Runs great 15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.
Q3_K_M 15.1 GB 57.6 GB 32.5 tok/s Runs great 18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.
Q4_K_M 16.7 GB 57.6 GB 25.1 tok/s Runs well 20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.
Q5_K_M 18.0 GB 57.6 GB 20.7 tok/s Runs well 21Basic quality (D) · 21 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.
Q6_K 19.5 GB 57.6 GB 17.4 tok/s Runs well 21Basic quality (D) · 21 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.
Q8_0 22.7 GB 57.6 GB 12.8 tok/s Runs well 22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.
F16 35.3 GB 57.6 GB 5.9 tok/s Slow 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (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

Quick answers

How much memory does LLaVA 1.5 13B need on the NVIDIA GB10 64GB?

At Q2_K it needs about 13.9 GB. The NVIDIA GB10 64GB has 57.6 GB usable.

How fast is LLaVA 1.5 13B on the NVIDIA GB10 64GB?

About 41.2 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of LLaVA 1.5 13B should I use on the NVIDIA GB10 64GB?

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.

Was this page helpful?