Home / Models / Yi 1.5 34B Chat / NVIDIA RTX A5000 24 GB
Can Yi 1.5 34B Chat run on NVIDIA RTX A5000 24 GB?
Yes. Calculated memory fit: Yi 1.5 34B Chat can run entirely in this GPU’s usable VRAM at one or more supported quantizations.
Can it run?
- Can it run?
- Yes, full GPU fit (calculated estimate).
- Full GPU fit?
- Yes
- Model
- Yi 1.5 34B Chat · 34B
- GPU
- NVIDIA RTX A5000 24 GB · 24 GB advertised
Memory calculation
Breakdown for Q4 at 4K context, batch size 1. Calculator v1.0.0.
| Model weights | 20.2 GB |
|---|---|
| KV cache | 0.9 GB |
| Runtime reserve | 1.5 GB |
| Safety margin | 0.9 GB |
| Required (estimated) | 23.5 GB |
| GPU usable VRAM | 21.6 GB |
Result: CPU RAM OFFLOAD REQUIRED
Quantization table
| Quantization | 2K | 4K |
|---|---|---|
| BF16 | No | No |
| FP16 | No | No |
| Q3 | Fits | Fits |
| Q4 | Offload | Offload |
| Q5 | Offload | Offload |
| Q6 | Offload | Offload |
| Q8 | Offload | Offload |
What fits entirely in VRAM?
- Q3 at 2K context
- Q3 at 4K context
What requires RAM offload?
Offload is shown only when the model does not fully fit in usable VRAM but stays within the modeled offload allowance.
Available graphics cards
These SKUs use this GPU chip. Amazon CTAs appear only for EXACT/HIGH matches. Absence of a price does not change the compatibility result above.
Lenovo 4X61D97085 graphics card NVIDIA RTX A5000 24 GB GDDR6
24 GB · Amazon EXACT
$2760.00
Check price on Amazon
Sources
Model: official config 01-ai/Yi-1.5-34B-Chat (main). GPU/product specs: Icecat. Compatibility: RigForAI calculator v1.0.0 estimated VRAM · Q8 at 4K: CPU_RAM_OFFLOAD_REQUIRED. Amazon: affiliate commerce match, not a spec source.