on

Can the NVIDIA H100 NVL run Zamba2 2.7B Instruct?

22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At F16 it needs about 11.0 GB of 94.0 GB usable, with an estimated speed of 422 tok/s.

Best quant
F16
Generation speed
422 tok/s
Prompt processing
32,481 tok/s
First token (1K prompt)
0.3 s
Largest safe context
4K

Best app to run it on the NVIDIA H100 NVL

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 Zyphra/Zamba2-2.7B-instruct
  • 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.
  • Docker Model Runner Handy if you already work in Docker.

On Windows

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.
  • On Windows it runs through WSL2.
vllm serve Zyphra/Zamba2-2.7B-instruct
  • 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.
  • Docker Model Runner Handy if you already work in Docker.

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 Zamba2 2.7B Instruct

Original weights · Hugging Face

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

huggingface.co/Zyphra/Zamba2-2.7B-instruct (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 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (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 H100 NVL: 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.9.9 / 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.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 score52.6 / 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 H100 NVL

Quant Memory needed Available Speed Runs Quality Download
Q2_K 6.7 GB 94.0 GB 2,956 tok/s Runs great 15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q3_K_M 7.0 GB 94.0 GB 2,327 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 50/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q4_K_M 7.3 GB 94.0 GB 1,800 tok/s Runs great 20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q5_K_M 7.6 GB 94.0 GB 1,487 tok/s Runs great 21Basic quality (D) · 21 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q6_K 7.9 GB 94.0 GB 1,249 tok/s Runs great 21Basic quality (D) · 21 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q8_0 8.5 GB 94.0 GB 916 tok/s Runs great 22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
F16 11.0 GB 94.0 GB 422 tok/s Runs great 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (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 Zamba2 2.7B Instruct need on the NVIDIA H100 NVL 94GB?

At F16 it needs about 11.0 GB. The NVIDIA H100 NVL 94GB has 94.0 GB usable.

How fast is Zamba2 2.7B Instruct on the NVIDIA H100 NVL 94GB?

About 422 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Zamba2 2.7B Instruct should I use on the NVIDIA H100 NVL 94GB?

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.

Was this page helpful?