Home / Models / Qwen2.5 32B Instruct
Qwen2.5 32B Instruct
33B parameters · native context 32,768 · qwen2
Estimated VRAM requirement
Weight memory uses parameter count × bits per weight, plus a quantization overhead factor. KV cache uses standard GQA formulas. Values are calculated estimates, not measured allocations.
| Quantization | Estimated weights | 2K total | 4K total | 8K total | 16K total | 32K total |
|---|---|---|---|---|---|---|
| FP16 | 61.7 GB | 67.9 GB | 68.4 GB | 69.4 GB | 71.4 GB | 75.4 GB |
| Q8 | 34.7 GB | 38.8 GB | 39.3 GB | 40.3 GB | 42.3 GB | 46.3 GB |
| Q6 | 27.1 GB | 30.5 GB | 31.0 GB | 32.0 GB | 34.0 GB | 38.0 GB |
| Q5 | 22.9 GB | 26.0 GB | 26.5 GB | 27.5 GB | 29.5 GB | 33.5 GB |
| Q4 | 19.1 GB | 21.8 GB | 22.3 GB | 23.3 GB | 25.3 GB | 29.3 GB |
| Q3 | 15.2 GB | 17.7 GB | 18.2 GB | 19.2 GB | 21.2 GB | 25.2 GB |
Find a GPU for this model
Run at the quantization and context selected below. Defaults are Q4 and 8K when you do not change the controls. Results are full-VRAM fits only — not a speed ranking.
- Run at
- Q4 · 8K context
- Required VRAM
- 23.3 GB
No fresh matched Amazon price is currently available for a full-VRAM fit. See compatible GPUs · Workstations · Rent a server · Buy vs rent.
Lowest-cost full-VRAM option
Sorted by lowest current Amazon price among GPUs that fit entirely in VRAM. This is not a performance ranking.
No compatible GPU currently has a fresh Amazon price.
More VRAM headroom
Sorted by leftover usable VRAM after the calculated requirement. Headroom is not tokens/sec.
NVIDIA B200 192 GB
- GPU VRAM
- 192 GB advertised
- Required VRAM
- 23.3 GB
- Usable GPU VRAM
- 172.8 GB
- VRAM headroom
- 149.5 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 0 mapped · 0 Amazon-matched
- Amazon
- Check availability
NVIDIA H200 141 GB
- GPU VRAM
- 141 GB advertised
- Required VRAM
- 23.3 GB
- Usable GPU VRAM
- 126.9 GB
- VRAM headroom
- 103.6 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 0 mapped · 0 Amazon-matched
- Amazon
- Check availability
NVIDIA GH200 96 GB
- GPU VRAM
- 96 GB advertised
- Required VRAM
- 23.3 GB
- Usable GPU VRAM
- 86.4 GB
- VRAM headroom
- 63.1 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 0 mapped · 0 Amazon-matched
- Amazon
- Check availability
Other compatible GPUs
NVIDIA RTX 5000 32 GB
- GPU VRAM
- 32 GB advertised
- Required VRAM
- 23.3 GB
- Usable GPU VRAM
- 28.8 GB
- VRAM headroom
- 5.5 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 2 mapped · 1 Amazon-matched
- Amazon
- Check price on Amazon
NVIDIA Tesla M10 32 GB
- GPU VRAM
- 32 GB advertised
- Required VRAM
- 23.3 GB
- Usable GPU VRAM
- 28.8 GB
- VRAM headroom
- 5.5 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 1 mapped · 0 Amazon-matched
- Amazon
- Check availability
NVIDIA Quadro GV100 32 GB
- GPU VRAM
- 32 GB advertised
- Required VRAM
- 23.3 GB
- Usable GPU VRAM
- 28.8 GB
- VRAM headroom
- 5.5 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 1 mapped · 0 Amazon-matched
- Amazon
- Check availability
Compatible GPUs
Status is a calculated memory fit against usable VRAM (advertised × 0.9). Open a GPU to see product SKUs and Amazon listings.
Compare GPUs for this model
Published chip comparisons where both GPUs fully fit this model at Q4 / 8K. Opens with this model preselected; that query is not indexed.
How fast can this model run?
llama.cpp CUDA decode at Q4 under llama-bench tg128 conditions. Not a ranking. Open a pair for prefill and methodology.
| GPU | Decode | State | Confidence |
|---|---|---|---|
| NVIDIA RTX 5090 32 GB | ~56 tok/s | Estimated | LOW |
| NVIDIA RTX A6000 48 GB | ~27 tok/s | Estimated | LOW |
Sources
Model specifications: official repository Qwen/Qwen2.5-32B-Instruct · revision main. Compatibility: RigForAI calculator v1.0.0 (estimated VRAM). GPU products: Icecat. Amazon is a separate affiliate match and is not used as a spec source.