MacBook Pro M4 Max 96GBOpção econômica
96 GB Unified (+48)
C
Adds memory headroom for longer context windows and future model growth.42 tok/s decodificação
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
Can AI21 Jamba Reasoning 3B run on NVIDIA L40S 48GB?
YES — Runs Great
C43Usable
Estimated from fit model
AI21 Jamba Reasoning 3B needs ~7.9 GB VRAM. NVIDIA L40S 48GB has 48.0 GB. With Q4_K_M quantization, expect ~48 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.
Select quantization to explore
Q4_K_M (Medium quality) — 7.9 GB, 48.0 tok/s, Runs well
7.9 GB required48.0 GB available
16% VRAM used
Fit status
Runs well
Decode
48.0 tok/s
TTFT
4033 ms
Safe context
1.8M
Memory
7.9 GB / 48.0 GB
Memory breakdown
Weights1.8 GB
KV Cache0.4 GB
Runtime0.9 GB
Headroom4.8 GB
See how fast it feels
See how fast it feelsAI21 Jamba Reasoning 3B on NVIDIA L40S 48GB
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: 48.0 tok/s decode · 4.0s TTFT (warm) · 120 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 | 48.0 tok/s | 2200 ms | 1.8M |
| Coding | C | Runs well | 48.0 tok/s | 4033 ms | 1.8M |
| Agentic Coding | C | Runs well | 48.0 tok/s | 5867 ms | 1.8M |
| Reasoning | C | Runs well | 48.0 tok/s | 4767 ms | 1.8M |
| RAG | C | Runs well | 48.0 tok/s | 7333 ms | 1.8M |
Quantization options
How AI21 Jamba Reasoning 3B (3B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.2 GB | Low | C41 |
Q3_K_S | 3 | 1.5 GB | Low | C41 |
NVFP4 | 4 | 1.7 GB | Medium | C41 |
Q4_K_M | 4 | 1.8 GB | Medium | C41 |
Q5_K_M | 5 | 2.2 GB | High | C41 |
Q6_K | 6 | 2.5 GB | High | C41 |
Q8_0 | 8 | 3.2 GB | Very High | C41 |
F16Best for your GPU | 16 | 6.1 GB | Maximum | C42 |
Get started
Copy-paste commands to run AI21 Jamba Reasoning 3B on your machine.
Run
lms load hf-ai21labs--ai21-jamba-reasoning-3b-gguf && lms server startOpções de upgrade
Hardware que roda bem AI21 Jamba Reasoning 3B
Frequently asked questions
Can NVIDIA L40S 48GB run AI21 Jamba Reasoning 3B?
Yes, NVIDIA L40S 48GB can run AI21 Jamba Reasoning 3B with a C grade (Runs well). Expected decode speed: 48.0 tok/s.
How much VRAM does AI21 Jamba Reasoning 3B need?
AI21 Jamba Reasoning 3B (3B parameters) requires approximately 7.9 GB of memory with Q4_K_M quantization.
What is the best quantization for AI21 Jamba Reasoning 3B?
The recommended quantization for AI21 Jamba Reasoning 3B is Q4_K_M, which balances quality and memory efficiency.
What speed will AI21 Jamba Reasoning 3B run at on NVIDIA L40S 48GB?
On NVIDIA L40S 48GB, AI21 Jamba Reasoning 3B achieves approximately 48.0 tokens per second decode speed with a time-to-first-token of 4033ms using Q4_K_M quantization.
Can NVIDIA L40S 48GB run AI21 Jamba Reasoning 3B for coding?
For coding workloads, AI21 Jamba Reasoning 3B on NVIDIA L40S 48GB receives a C grade with 48.0 tok/s and 1.8M context.
What context window can AI21 Jamba Reasoning 3B use on NVIDIA L40S 48GB?
On NVIDIA L40S 48GB, AI21 Jamba Reasoning 3B can safely use up to 1.8M tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-ai21labs--ai21-jamba-reasoning-3b-gguf-on-l40s-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: