Can an Arc B580 run Qwen3.5 27B?
Barely
It only loads at IQ3_XXS, which compresses the weights far enough to visibly degrade the model, so we would not call that running it.
In practice
It loads, and we would not call that running it. The only quantization that fits the Arc B580 is IQ3_XXS, which compresses the weights far enough that Qwen3.5 27B loses a visible amount of its ability, so we do not recommend it. At Q4_K_M it needs 15.99 GB against the 11.2 GB available.
Running it properly means a split with system RAM: at Q4_K_M about 44 of 64 layers fit on the card, and the estimate falls to 4.9 tokens per second. A smaller model at a proper quantization is a better answer than a larger one squeezed in, and the next section lists the ones that fit.
The numbers
Qwen3.5 27B has 27.78 billion parameters across 64 layers. The Arc B580 has 12 GB of VRAM at 456 GB/s, of which about 11.2 GB is left for a model once the operating system has taken its share.
| Quantization | Total needed | Fits | Speed |
|---|---|---|---|
| Q8_0 | 27.32 GB | partial | 1.7 t/s |
| Q6_K | 21.33 GB | partial | 2.6 t/s |
| Q5_K_M | 18.64 GB | partial | 3.4 t/s |
| Q4_K_M | 15.99 GB | partial | 4.9 t/s |
| IQ4_XS | 14.2 GB | partial | 7.0 t/s |
| Q3_K_M | 13.15 GB | partial | 9.3 t/s |
| IQ3_XXS degraded | 10.53 GB | yes | 25.7 t/s |
| Q2_K degraded | 11.42 GB | partial | 19.0 t/s |
| IQ2_XXS degraded | 7.44 GB | yes | 37.0 t/s |
2 of the 9 levels fit entirely. Levels marked degraded are listed for completeness, not as advice. Rows marked partial or experts in RAM run with part of the model in system RAM, at the speed shown.
What to run instead
A smaller model from the same family is the straightforward answer. These fit on an Arc B580 at a quantization worth using:
- Qwen3 14B, 14.77B at Q5_K_M, 10.96 GB, about 24.6 tokens/s
- Qwen2.5 14B Instruct, 14.77B at Q4_K_M, 9.81 GB, about 27.7 tokens/s
- Qwen2.5 Coder 14B Instruct, 14.77B at Q4_K_M, 9.81 GB, about 27.7 tokens/s
Shortening the context will not rescue this one: at 4k it still wants 15.74 GB against 15.99 GB at 8k, because the weights, not the cache, are what fill the card.
Or the hardware that does run it
The cheapest device we track that runs Qwen3.5 27B at a quantization worth using is the Arc A770 16GB, around $280 used , running it at IQ4_XS at about 23.1 tokens per second. Check the current price (affiliate link, indicative price reviewed 2026-09-01). Compare every option.
What else an Arc B580 runs well
For comparison, these are the other popular models that fit this device at a sound quantization, best pairings first.
| Model | Quantization | Memory | Speed |
|---|---|---|---|
| Gemma 4 12B Instruct | Q6_K | 10.84 GB | 24.8 t/s |
| Qwen3.5 9B | Q8_0 | 9.25 GB | 29.3 t/s |
| Qwen3 14B | Q5_K_M | 10.96 GB | 24.6 t/s |
| Qwen3 8B | Q8_0 | 9.02 GB | 30.1 t/s |
The same model on nearby hardware
Memory decides whether Qwen3.5 27B loads and bandwidth decides how quickly it answers. Here is what a step down, a card with the same memory and a step up do with it.
| Device | Memory | Bandwidth | Result |
|---|---|---|---|
| GeForce RTX 3070 | 8 GB | 448 GB/s | partial, 3.1 t/s |
| GeForce RTX 4070 | 12 GB | 504 GB/s | does not fit |
| GeForce RTX 5080 | 16 GB | 960 GB/s | IQ4_XS, 51.3 t/s |
Questions people ask
How much VRAM does Qwen3.5 27B need on Arc B580?
At Q4_K_M with an 8k context window it needs 15.99 GB in total: 14.91 GB of weights, 0.64 GB of KV cache and 0.44 GB of runtime overhead. The Arc B580 makes about 11.2 GB available once the operating system has taken its share.
What should I run instead of Qwen3.5 27B on Arc B580?
Qwen3 14B fits at Q5_K_M and runs at about 24.6 tokens per second. Smaller models from the same family are the usual answer.
Keep going
Everything the Arc B580 runs, the full breakdown for Qwen3.5 27B, how the numbers are made in the methodology, or a different pairing in the calculator.