- 3 % discount on prepayment
- Insured shipping from Switzerland
- Sustainable: refurbished instead of new
- Warranty on all cards
- 3 % discount on prepayment
- Insured shipping from Switzerland
- Sustainable: refurbished instead of new
- Warranty on all cards
← Back to overview
Qwen3-Coder-Next
Alibaba (Qwen)
Apache 2.0
Open model for programmers. 79.7B Parameter, partly mixture-of-experts (only a part of the parameters is active per token).
- Mixture-of-experts: 79.7B parameters in total, of which 3.9B active per token. Memory requirement depends on all parameters, speed on the active ones.
Settings
Quality
4 bit (Q4_K_M) is the most common choice: good quality with low memory requirements.
Context length: 8k tokens
4k256k
How much text the model keeps in view at once. More context needs more memory.
Recommendation
1× H100 80 GB
The model needs about 49.5 GB of memory. Hopper, FP8 support.
- Weights
- 47.8 GB
- KV cache
- 0.2 GB
- Speed
- ~419.1 Tok./s
More suitable configurations
| Card | Quantity | Tok./s | Status |
|---|---|---|---|
| Tesla T4 16 GB | 4× | 58.5 | 2-3 weeks delivery time |
| Tesla P100 16 GB | 4× | 73.7 | 2-3 weeks delivery time |
| Tesla P40 24 GB | 4× | 69.1 | 2-3 weeks delivery time |
| Tesla V100 16 GB | 4× | 162.9 | only 1 in stock |
| Tesla V100 32 GB | 2× | 187.0 | On order, delivery time approx. 1 week |
| AMD Instinct MI50 16 GB | 4× | 124.9 | only 2 in stock |
| AMD Instinct MI50 32 GB | 2× | 143.4 | in stock |
| AMD Instinct MI60 32 GB | 2× | 132.4 | 2-3 weeks delivery time |
| AMD Instinct MI100 32 GB | 2× | 160.1 | 2-3 weeks delivery time |
| A30 24 GB | 4× | 157.6 | 2-3 weeks delivery time |
| RTX A5000 24 GB | 4× | 164.2 | 2-3 weeks delivery time |
| A40 48 GB | 2× | 179.8 | 2-3 weeks delivery time |
