Can AI21 Jamba Reasoning 3B run on Intel Arc A770 16GB?

YES — Runs Great

C45Usable

○Estimated from fit model

AI21 Jamba Reasoning 3B needs ~4.7 GB VRAM. Intel Arc A770 16GB has 16.0 GB. With Q4_K_M quantization, expect ~42 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: MediumStack: 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) — 4.7 GB, 42.0 tok/s, Runs well

4.7 GB required16.0 GB available

29% VRAM used

Fit status

Runs well

Decode

42.0 tok/s

TTFT

4610 ms

Safe context

531K

Memory

4.7 GB / 16.0 GB

Memory breakdown

Weights1.8 GB

KV Cache0.4 GB

Runtime0.9 GB

Headroom1.6 GB

See how fast it feels

See how fast it feelsAI21 Jamba Reasoning 3B on Intel Arc A770 16GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.

Given information:
 - Speed = 60 mph (miles per hour)
 - Time = 2.5 hours

Formula: Distance = Speed x Time

Calculation:
 Distance = 60 mph x 2.5 h
 = 150 miles

The train travels 150 miles.

Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.

Breakdown:
 - First half: 1.25 hours at 60 mph = 75 miles
 - Stop: 20 minutes (no distance)
 - Second half: 1.25 hours at 60 mph = 75 miles

Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph

The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 42.0 tok/s decode · 4.6s TTFT (warm) · 105 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	42.0 tok/s	2514 ms	531K
Coding	C	Runs well	42.0 tok/s	4610 ms	531K
Agentic Coding	C	Runs well	42.0 tok/s	6705 ms	531K
Reasoning	C	Runs well	42.0 tok/s	5448 ms	531K
RAG	C	Runs well	42.0 tok/s	8381 ms	531K