HelpingAI2.5 10B i1 needs ~11.7 GB VRAM. RTX 5090 32GB has 32.0 GB. With Q4_K_M quantization, expect ~140 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
140.0 tok/s
TTFT
1383 ms
Safe context
294K
Memory
11.7 GB / 32.0 GB
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 140.0 tok/s | 754 ms | 294K |
| Coding | C | Runs well | 140.0 tok/s | 1383 ms | 294K |
| Agentic Coding | C | Runs well | 140.0 tok/s | 2011 ms | 294K |
| Reasoning | C | Runs well | 140.0 tok/s | 1634 ms | 294K |
| RAG | C | Runs well | 140.0 tok/s | 2514 ms | 294K |
How HelpingAI2.5 10B i1 (10B params) fits at each quantization level on RTX 5090 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.9 GB | Low | C43 |
Q3_K_S | 3 | 4.9 GB | Low | C43 |
NVFP4 | 4 |
Copy-paste commands to run HelpingAI2.5 10B i1 on your machine.
Run
lms load hf-mradermacher--helpingai2-5-10b-i1-gguf && lms server startYes, RTX 5090 32GB can run HelpingAI2.5 10B i1 with a C grade (Runs well). Expected decode speed: 140.0 tok/s.
HelpingAI2.5 10B i1 (10B parameters) requires approximately 11.7 GB of memory with Q4_K_M quantization.
The recommended quantization for HelpingAI2.5 10B i1 is Q4_K_M, which balances quality and memory efficiency.
On RTX 5090 32GB, HelpingAI2.5 10B i1 achieves approximately 140.0 tokens per second decode speed with a time-to-first-token of 1383ms using Q4_K_M quantization.
For coding workloads, HelpingAI2.5 10B i1 on RTX 5090 32GB receives a C grade with 140.0 tok/s and 294K context.
On RTX 5090 32GB, HelpingAI2.5 10B i1 can safely use up to 294K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-mradermacher--helpingai2-5-10b-i1-gguf-on-rtx-5090-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| Medium |
| C43 |
Q4_K_M | 4 | 6.1 GB | Medium | C44 |
Q5_K_M | 5 | 7.2 GB | High | C44 |
Q6_K | 6 | 8.2 GB | High | C44 |
Q8_0 | 8 | 10.7 GB | Very High | C46 |
F16Best for your GPU | 16 | 20.5 GB | Maximum | C49 |