Home / Models / Vicuna 7B v1.5 / NVIDIA Tesla K40 12 GB
Calculated memory fit · not a benchmark
Can Vicuna 7B v1.5 run on NVIDIA Tesla K40 12 GB?
Yes. Calculated memory fit: Vicuna 7B v1.5 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
- Vicuna 7B v1.5 · 6.7B
- GPU
- NVIDIA Tesla K40 12 GB · 12 GB advertised
Memory calculation
Breakdown for Q4 at 4K context, batch size 1. Calculator v1.0.0.
| Model weights | 4.0 GB |
|---|---|
| KV cache | 2.0 GB |
| Runtime reserve | 0.7 GB |
| Safety margin | 0.4 GB |
| Required (estimated) | 7.0 GB |
| GPU usable VRAM | 10.8 GB |
Result: FITS IN VRAM
Quantization table
| Quantization | 2K | 4K |
|---|---|---|
| BF16 | Offload | Offload |
| FP16 | Offload | Offload |
| Q3 | Fits | Fits |
| Q4 | Fits | Fits |
| Q5 | Fits | Fits |
| Q6 | Fits | Fits |
| Q8 | Fits | Fits |
What fits entirely in VRAM?
- Q3 at 2K context
- Q3 at 4K context
- Q4 at 2K context
- Q4 at 4K context
- Q5 at 2K context
- Q5 at 4K context
- Q6 at 2K context
- Q6 at 4K context
- Q8 at 2K context
- Q8 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.
Sources
Model: official config lmsys/vicuna-7b-v1.5 (main). GPU/product specs: Icecat. Compatibility: RigForAI calculator v1.0.0 estimated VRAM · Q8 at 4K: FITS_IN_VRAM. Amazon: affiliate commerce match, not a spec source.