Can the Arc A310 run Qwen3.8-27B-DSpine-b16?
Qwen3.8-27B-DSpine-b16·2B·Arc A310·4 GB VRAM
Yes. The Arc A310 runs Qwen3.8-27B-DSpine-b16 fully in VRAM at Q8_0 (about 2.8 GB of 4.0 GB), at roughly 32 tokens/s.
- best quant
- Q8_0
- needs
- 2.8 GB
- usable
- 4.0 GB
- est. speed
- ~32 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Qwen3.8-27B-DSpine-b16 page →
Every quantisation of Qwen3.8-27B-DSpine-b16 on the Arc A310
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 1.3 GB | fits | ~102 tok/s |
| Q3_K_M | 1.6 GB | fits | ~69 tok/s |
| Q4_K_M | 1.9 GB | fits | ~56 tok/s |
| Q5_K_M | 2.1 GB | fits | ~47 tok/s |
| Q6_K | 2.3 GB | fits | ~41 tok/s |
| Q8_0 pick | 2.8 GB | fits | ~32 tok/s |
| FP16 / BF16 | 4.6 GB | offload | ~15 tok/s |
Speed is a bandwidth-based estimate for generating text (124 GB/s); prompt processing and long contexts are slower.
Measured speed on the Arc A310
No community reports for this pair yet.
Report your own speed →Chat models that fit the Arc A310 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 2B | Q8_0 | ≈3.2 GBFits in memory | ~32 tok/s | |
| 1.7B | Q8_0 | ≈2.7 GBFits in memory | ~37 tok/s | |
| 2.5B | Q8_0 | ≈3.5 GBFits in memory | ~26 tok/s | |
| 1.5B | Q8_0 | ≈2.6 GBFits in memory | ~42 tok/s | |
| 2.6B | Q6_K | ≈3.4 GBFits in memory | ~32 tok/s | |
| 3.2B | Q5_K_M | ≈3.6 GBFits in memory | ~30 tok/s |
Other GPUs that run Qwen3.8-27B-DSpine-b16
Frequently asked questions
- Can the Arc A310 run Qwen3.8-27B-DSpine-b16?
- Yes. The Arc A310 runs Qwen3.8-27B-DSpine-b16 fully in VRAM at Q8_0 (about 2.8 GB of 4.0 GB), at roughly 32 tokens/s.
- How fast does Qwen3.8-27B-DSpine-b16 run on the Arc A310?
- An estimate from memory bandwidth gives about 32 tokens/s at Q8_0.
- Which quantisation of Qwen3.8-27B-DSpine-b16 should I use on the Arc A310?
- Q8_0: the largest one that fits. Expected quality: lossless compared with the full-precision weights.
Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.