AI21 Jamba Large 1.5 — Hardware Requirements & GPU Compatibility
Chat
AI21 Jamba Large 1.5 is a 398.6B-parameter open language model from AI21 Labs in the Jamba family. At BF16 it needs about 876.82 GB of VRAM — see which GPUs and Macs can run it below.
AI21 Jamba Large 1.5 runs on a multi-GPU server
BF16 needs ~884.5 GB · about 7× H200 SXM 141 GB
Other
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run AI21 Jamba Large 1.5
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve ai21labs/AI21-Jamba-Large-1.5 --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Rent 7× H200 SXM · BF16
- Estimated hourly price
- ~$25.13/hr
- est., whole server
- GPUs
- 7 GPUs
- 987 GB of VRAM
$5+ bonus for new users
How Much VRAM Does AI21 Jamba Large 1.5 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 876.8 GB | 893.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 7× H200 SXM 141 GB |
Selected BF16
Brain floating point 16884.5GBat 16K context
- Weights
- 875.4 GB
- KV cache
- 8.8 GB
- Overhead
- 0.3 GB
Server-class: ~884.5 GB at 16K context · about 7× H200 SXM 141 GB
Which Hardware Can Run AI21 Jamba Large 1.5?
BF16 · 876.8 GBAI21 Jamba Large 1.5 (BF16) requires 876.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1140+ GB is recommended. No consumer GPU has enough memory.
Needs server-class hardware
AI21 Jamba Large 1.5 runs on a multi-GPU server · BF16 needs ~884.5 GB
| Hardware | Quant | Memory | Context | Hardware page | |
|---|---|---|---|---|---|
| 7× H200 SXM 141 GB · 987 GB | BF16 | 884.5 GB | 16K ctx | H200 SXM → | BF16 · 884.5 GB · 16K ctx |
| 6× B200 192 GB · 1.2 TB | BF16 | 884.5 GB | 32K ctx | B200 → | BF16 · 884.5 GB · 32K ctx |
By VRAM tier · typical GPUs and Macs at BF16
Consumer GPUs (up to 32 GB) and Macs up to 512 GB: too small for this model (needs ≥ 884.5 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
How good is AI21 Jamba Large 1.5?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
Here are all 2 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- LMArena Text
LMArena · Oct 2026Arena
Arena1289.5
#114/188 open
- MMLU-Pro
TIGER-LabIndependent
Independent49.5%
#76/146 open
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Llama 4 Maverick 17B 128E InstructMeta | 87.1 | 272.7 GB | —needs > 24 GB | same size |
| Llama 3.1 405B InstructMeta | 83.5 | 275.6 GB | —needs > 24 GB | same size |
| MiniMax M3.1 FlashMiniMax | — | 258.6 GB | —needs > 24 GB | same size |
| Intern S2 397BInternLM | — | 242.6 GB | —needs > 24 GB | same size |
| Ornith 1.5 397Bornith-ai | — | 242.6 GB | —needs > 24 GB | same size |
| Trinity Large ThinkingArcee AI | — | 799.6 GB | —needs > 24 GB | same size |
Frequently Asked Questions
How much VRAM does AI21 Jamba Large 1.5 need?
AI21 Jamba Large 1.5 requires 876.8 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 398.6B × 16 bits ÷ 8 = 797.1 GB
KV Cache + Overhead ≈ 79.7 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run AI21 Jamba Large 1.5?
No — AI21 Jamba Large 1.5 requires at least 876.8 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run AI21 Jamba Large 1.5 on a Mac?
AI21 Jamba Large 1.5 requires at least 876.8 GB at BF16. None of the 146 Macs we list has that much usable memory (the largest has 508.5 GB after macOS overhead).
Can I run AI21 Jamba Large 1.5 locally?
Yes — AI21 Jamba Large 1.5 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of AI21 Jamba Large 1.5?
At BF16, the download is about 797.11 GB.
Which GPUs can run AI21 Jamba Large 1.5?
No single consumer GPU has enough VRAM to run AI21 Jamba Large 1.5 at BF16 (876.8 GB). Multi-GPU or professional hardware is required.
Which devices can run AI21 Jamba Large 1.5?
AI21 Jamba Large 1.5 requires at least 876.8 GB at BF16, which exceeds the usable memory of every unified-memory device we list (the largest has 508.5 GB).