AI21 Jamba Reasoning 3B needs ~20.8 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With F16 quantization, expect ~37 tok/s.
Operating mode
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
Fit status
Runs well
Decode
42.0 tok/s
TTFT
4610 ms
Safe context
4.2M
Memory
16.4 GB / 108.8 GB
This setup is broadly balanced for this model.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 16.1 tok/s | 6554 ms | 4K |
| Coding | F | Too heavy | 16.1 tok/s | 12016 ms | 4K |
| Agentic Coding | F | Too heavy | 16.1 tok/s | 17478 ms | 4K |
| Reasoning | F | Too heavy | 16.1 tok/s | 14201 ms | 4K |
| RAG | F | Too heavy | 16.1 tok/s | 21848 ms | 4K |
How AI21 Jamba Reasoning 3B (3B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.2 GB | Low | D39 |
Q3_K_S | 3 | 1.5 GB | Low | D39 |
NVFP4 | 4 | 1.7 GB | Medium | D39 |
Q4_K_M | 4 | 1.8 GB | Medium | D39 |
Q5_K_M | 5 | 2.2 GB | High | D39 |
Q6_K | 6 | 2.5 GB | High | D39 |
Q8_0 | 8 | 3.2 GB | Very High | D39 |
F16Best for your GPU | 16 | 6.1 GB | Maximum | D39 |
Copy-paste commands to run AI21 Jamba Reasoning 3B on your machine.
Run
lms load hf-ai21labs--ai21-jamba-reasoning-3b-gguf && lms server startUpgrade-Optionen
Yes, NVIDIA DGX Spark 128GB can run AI21 Jamba Reasoning 3B at F16 quantization (Runs well). The recommended Q4_K_M requires 3.4 GB which exceeds available memory, but at F16 it needs only 20.8 GB. Expected decode speed: 37.3 tok/s.
AI21 Jamba Reasoning 3B (3B parameters) requires approximately 3.4 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at F16 using 20.8 GB.
The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is F16, which uses 20.8 GB.
On NVIDIA DGX Spark 128GB, AI21 Jamba Reasoning 3B achieves approximately 37.3 tokens per second decode speed with a time-to-first-token of 5192ms using F16 quantization.
For coding workloads, AI21 Jamba Reasoning 3B on NVIDIA DGX Spark 128GB receives a F grade with 16.1 tok/s and 4K context.
On NVIDIA DGX Spark 128GB, AI21 Jamba Reasoning 3B can safely use up to 4.0M tokens of context at F16 quantization. The model's official context limit is —, but available memory constrains the safe maximum.
Not always. NVIDIA DGX Spark 128GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
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-dgx-spark-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: