Can AI21 Jamba2 3B i1 run on AMD Instinct MI350X 288GB?

YES — Runs Great

C41Usable

Estimated from fit model

AI21 Jamba2 3B i1 needs ~31.9 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~42 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 31.9 GB, 42.0 tok/s, Runs well

31.9 GB required288.0 GB available

11% VRAM used

Fit status

Runs well

Decode

42.0 tok/s

TTFT

4610 ms

Safe context

11.7M

Memory

31.9 GB / 288.0 GB

Memory breakdown

Weights1.8 GB

KV Cache0.4 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsAI21 Jamba2 3B i1 on AMD Instinct MI350X 288GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.

When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.

Key benefits of running locally:
  - Full privacy: your prompts never leave your machine
  - No per-token cost or rate limits
  - Works offline once the model is downloaded
  - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:

  Model size     Q4 (4-bit)    Q8 (8-bit)    FP16
  7B params      ~4.3 GB       ~7.5 GB       ~14 GB
  13B params     ~7.9 GB       ~13.9 GB      ~26 GB
  70B params     ~42.7 GB      ~74.9 GB      ~140 GB

Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 42.0 tok/s decode · 4.6s TTFT (warm) · 105 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	42.0 tok/s	2514 ms	11.7M
Coding	C	Runs well	42.0 tok/s	4610 ms	11.7M
Agentic Coding	C	Runs well	42.0 tok/s	6705 ms	11.7M
Reasoning	C	Runs well	42.0 tok/s	5448 ms	11.7M
RAG	C	Runs well	42.0 tok/s	8381 ms	11.7M

Inference speed

AI21 Jamba2 3B i1 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for AI21 Jamba2 3B i1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~57 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	57.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	48.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	48.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	42.0	Fits
RTX 4070 12GB	12 GB	Q4_K_M	42.0	Fits
RTX 3060 12GB	12 GB	Q4_K_M	42.0	Fits
RTX 4060 8GB	8 GB	Q4_K_M	42.0	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	42.0	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	42.0	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	42.0	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	42.0	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	42.0	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	42.0	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	42.0	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	42.0	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	42.0	Fits

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How AI21 Jamba2 3B i1 (3B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	1.2 GB	Low	D35
Q3_K_S	3	1.5 GB	Low	D35
NVFP4	4	1.7 GB	Medium	D35
Q4_K_M	4	1.8 GB	Medium	D35
Q5_K_M	5	2.2 GB	High	D35
Q6_K	6	2.5 GB	High	D35
Q8_0	8	3.2 GB	Very High	D35
F16Best for your GPU	16	6.1 GB	Maximum	D35

Get started

Copy-paste commands to run AI21 Jamba2 3B i1 on your machine.

Run

lms load hf-mradermacher--ai21-jamba2-3b-i1-gguf && lms server start

Frequently asked questions

Can AMD Instinct MI350X 288GB run AI21 Jamba2 3B i1?

Yes, AMD Instinct MI350X 288GB can run AI21 Jamba2 3B i1 with a C grade (Runs well). Expected decode speed: 42.0 tok/s.

How much VRAM does AI21 Jamba2 3B i1 need?

AI21 Jamba2 3B i1 (3B parameters) requires approximately 31.9 GB of memory with Q4_K_M quantization.

What is the best quantization for AI21 Jamba2 3B i1?

The recommended quantization for AI21 Jamba2 3B i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will AI21 Jamba2 3B i1 run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, AI21 Jamba2 3B i1 achieves approximately 42.0 tokens per second decode speed with a time-to-first-token of 4610ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run AI21 Jamba2 3B i1 for coding?

For coding workloads, AI21 Jamba2 3B i1 on AMD Instinct MI350X 288GB receives a C grade with 42.0 tok/s and 11.7M context.

What context window can AI21 Jamba2 3B i1 use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, AI21 Jamba2 3B i1 can safely use up to 11.7M tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for AI21 Jamba2 3B i1

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/hf-mradermacher--ai21-jamba2-3b-i1-gguf-on-instinct-mi350x-288gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: