LLMs ·

Jamba 1.5 Large

Parameters
399B (94.0B active)
Architecture
Mixture of experts
Max context
256K tokens
License
jamba-open-model
Released
2024-08

How to run it

Original weights · Hugging Face

Full-precision files from AI21 Labs, for fine-tuning, vLLM, Transformers.

huggingface.co/ai21labs/AI21-Jamba-Large-1.5 (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

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

Apps that run Jamba 1.5 Large

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 ai21labs/AI21-Jamba-Large-1.5
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path ai21labs/AI21-Jamba-Large-1.5
Docker Model Runner CLI + API Original weights macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/ai21labs/AI21-Jamba-Large-1.5
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-Transformer: only the attention layers keep a KV cache.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 159 GB 160 GB 161 GB All files (opens in a new tab)
Q3_K_M Low 195 GB 196 GB 197 GB All files (opens in a new tab)
Q4_K_M Good 243 GB 244 GB 245 GB All files (opens in a new tab)
Q5_K_M High 283 GB 284 GB 285 GB All files (opens in a new tab)
Q6_K High 327 GB 328 GB 329 GB All files (opens in a new tab)
Q8_0 Very high 422 GB 423 GB 424 GB All files (opens in a new tab)
F16 Full 797 GB 798 GB 799 GB Original weights (opens in a new tab)

Best hardware for Jamba 1.5 Large

Quality Hardware Quant Memory Speed Runs
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (2025) (M4 Max or M3 Ultra)Apple M3 Ultra (512 GB) Q3_K_M 227 GB / 384 GB 11.5 tok/s Runs well
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. Apple Mac Studio (2025) (M4 Max or M3 Ultra)Apple M3 Ultra (256 GB) Q2_K 176 GB / 192 GB 14.4 tok/s Runs welltight 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. AMD Instinct MI350XAMD Instinct MI350X Q4_K_M 258 GB / 288 GB 69.1 tok/s Runs welltight fit
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI325XAMD Instinct MI325X Q3_K_M 209 GB / 256 GB 68.0 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 81/100 (quality, fit, speed and memory use) sets the ranking. Dell Pro Max with GB300NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip Q3_K_M 209 GB / 252 GB 86.3 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 78/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (M5 Max or M5 Ultra)Apple M5 Ultra (512 GB) Q4_K_M 275 GB / 384 GB 12.9 tok/s Runs well
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI300XAMD Instinct MI300X Q2_K 170 GB / 192 GB 75.0 tok/s Runs welltight fit
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200NVIDIA B200 Q2_K 169 GB / 180 GB 112 tok/s Runs welltight fit
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (M5 Max or M5 Ultra)Apple M5 Ultra (256 GB) Q2_K 176 GB / 192 GB 20.7 tok/s Runs welltight fit
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (2023) (M2 Max or M2 Ultra)Apple M2 Ultra (192 GB) Q2_K 172 GB / 144 GB 12.0 tok/s Slowfar over GPU memory limit

Check it on your own hardware

Run it on a cluster

Devices that can’t run Jamba 1.5 Large alone can run it together. These example clusters do:

Try it with your own devices

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?