LLMs ·

Zamba2 2.7B Instruct

Parameters
2.7B
Architecture
Dense
Max context
4K tokens
License
apache-2.0
Released
2024-08

How to run it

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.

Apps that run Zamba2 2.7B Instruct

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, AMD Radeon

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux server, 80 GB+ GPUs

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.

Also good:

App Type Opens it as Systems Engine Start
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve Zyphra/Zamba2-2.7B-instruct
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path Zyphra/Zamba2-2.7B-instruct
Docker Model Runner CLI + API Original weights macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/Zyphra/Zamba2-2.7B-instruct
Text Generation WebUI Desktop app Original weights macOSWindowsLinux llama.cpp, Transformers, ExLlamaV3 Get Text Generation WebUI

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

KV cache: hybrid Mamba with shared attention blocks: only those blocks keep a KV cache.

Quantization Quality Weights Total at 4K context Download
Q2_K Low 1.1 GB 2.0 GB All files (opens in a new tab)
Q3_K_M Low 1.3 GB 2.3 GB All files (opens in a new tab)
Q4_K_M Good 1.6 GB 2.6 GB All files (opens in a new tab)
Q5_K_M High 1.9 GB 2.9 GB All files (opens in a new tab)
Q6_K High 2.2 GB 3.2 GB All files (opens in a new tab)
Q8_0 Very high 2.8 GB 3.8 GB All files (opens in a new tab)
F16 Full 5.3 GB 6.3 GB Original weights (opens in a new tab)

Best hardware for Zamba2 2.7B Instruct

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q6_K.

Quality Hardware Quant Memory Speed Runs
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPERNVIDIA GeForce RTX 4070 SUPER F16 6.9 GB / 12.0 GB 54.6 tok/s Runs great
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060NVIDIA GeForce RTX 4060 Q8_0 4.2 GB / 8.0 GB 63.9 tok/s Runs great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Sapphire NITRO+ AMD Radeon RX 9070 XT OCAMD Radeon RX 9070 XT F16 7.1 GB / 16.0 GB 59.7 tok/s Runs great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPERNVIDIA GeForce RTX 4070 Ti SUPER F16 7.1 GB / 16.0 GB 72.8 tok/s Runs great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPERNVIDIA GeForce RTX 4080 SUPER F16 7.1 GB / 16.0 GB 79.7 tok/s Runs great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. ASUS Dual GeForce RTX 5060 Ti 16GB GDDR7 OC EditionNVIDIA GeForce RTX 5060 Ti 16GB F16 7.1 GB / 16.0 GB 48.5 tok/s Runs great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. ASUS TUF Gaming GeForce RTX 5070 Ti 16GB GDDR7 OC EditionNVIDIA GeForce RTX 5070 Ti F16 7.1 GB / 16.0 GB 97.0 tok/s Runs great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Founders EditionNVIDIA GeForce RTX 5080 F16 7.1 GB / 16.0 GB 104 tok/s Runs great
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 Limited EditionIntel Arc B580 Q8_0 4.4 GB / 12.0 GB 81.8 tok/s Runs great
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GBNVIDIA GeForce RTX 3060 12GB Q8_0 4.4 GB / 12.0 GB 84.6 tok/s Runs great

Check it on your own hardware

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?