Home / Models / Qwen2.5-Coder 7B Instruct
Qwen2.5-Coder 7B Instruct
7.6B 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 | 14.5 GB | 16.5 GB | 16.6 GB | 16.8 GB | 17.3 GB | 18.1 GB |
| Q8 | 8.1 GB | 9.7 GB | 9.8 GB | 10.0 GB | 10.4 GB | 11.3 GB |
| Q6 | 6.3 GB | 7.7 GB | 7.8 GB | 8.0 GB | 8.5 GB | 9.4 GB |
| Q5 | 5.4 GB | 6.7 GB | 6.8 GB | 7.0 GB | 7.4 GB | 8.3 GB |
| Q4 | 4.5 GB | 5.7 GB | 5.8 GB | 6.0 GB | 6.5 GB | 7.3 GB |
| Q3 | 3.6 GB | 4.7 GB | 4.8 GB | 5.0 GB | 5.5 GB | 6.4 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
- 6.0 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
- 6.0 GB
- Usable GPU VRAM
- 172.8 GB
- VRAM headroom
- 166.8 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
- 6.0 GB
- Usable GPU VRAM
- 126.9 GB
- VRAM headroom
- 120.9 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
- 6.0 GB
- Usable GPU VRAM
- 86.4 GB
- VRAM headroom
- 80.4 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
AMD Radeon RX 470 8 GB
- GPU VRAM
- 8 GB advertised
- Required VRAM
- 6.0 GB
- Usable GPU VRAM
- 7.2 GB
- VRAM headroom
- 1.2 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 P4000 8 GB
- GPU VRAM
- 8 GB advertised
- Required VRAM
- 6.0 GB
- Usable GPU VRAM
- 7.2 GB
- VRAM headroom
- 1.2 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 6 mapped · 2 Amazon-matched
- Amazon
- Check price on Amazon
AMD Radeon RX 580 8 GB
- GPU VRAM
- 8 GB advertised
- Required VRAM
- 6.0 GB
- Usable GPU VRAM
- 7.2 GB
- VRAM headroom
- 1.2 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 13 mapped · 4 Amazon-matched
- Amazon
- Check price on Amazon
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 | ~239 tok/s | Calibrated estimate | HIGH |
| NVIDIA RTX 4090 24 GB | ~150 tok/s | Calibrated estimate | HIGH |
| NVIDIA RTX 5080 16 GB | ~147 tok/s | Calibrated estimate | HIGH |
| NVIDIA RTX 5070 Ti 16 GB | ~145 tok/s | Calibrated estimate | HIGH |
| NVIDIA RTX 3090 Ti 24 GB | ~137 tok/s | Calibrated estimate | HIGH |
| NVIDIA RTX 3090 24 GB | ~129 tok/s | Calibrated estimate | HIGH |
| NVIDIA RTX 4080 SUPER 16 GB | ~117 tok/s | Calibrated estimate | HIGH |
| NVIDIA RTX A6000 48 GB | ~115 tok/s | Calibrated estimate | HIGH |
| NVIDIA RTX 4080 16 GB | ~114 tok/s | Calibrated estimate | HIGH |
| NVIDIA RTX 3080 10 GB | ~111 tok/s | Calibrated estimate | HIGH |
Sources
Model specifications: official repository Qwen/Qwen2.5-Coder-7B-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.