Skip to content
Run LLM Locally

Qwen2.5 14B Instruct on the Arc B580

Qwen2.5 14B Instruct at Q4_K_M needs about 11.3 GB; the Arc B580 has 12 GB: it fits with almost no margin at 8K context. At Q8_0 it does not fit in VRAM.

ShareFacebookXWhatsAppLinkedInEmail

Qwen2.5 14B Instruct

Q4_K_M · 8K context

Compatible with limits

The model needs about 11.3 GB (up to 11.9 GB) for 11.6 GB available: it fits, but with almost no margin. Use a shorter context or a smaller quantization if loading fails.

Your hardware
Arc B580 12 GB · 64 GB RAM
Estimated memory
~11.3 GB estimate
VRAM (usable memory)
11.6 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
18–27 tok/s estimate
Largest context in fast memory
9K tokens
Confidence: low

Based on: memory bandwidth (456 GB/s) and model size

Memory breakdown

~11.3 GB (10.7 GB–11.9 GB) needed · estimate

Fits entirely in VRAM · 0.4 GB left

  • Model weights8.4 GB
  • KV cache1.5 GB
  • Runtime overhead0.9 GB
  • Safety margin0.5 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (SYCL) · flash attention on · weights = real file size

EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card

What makes this estimate less reliable

  • no benchmark for this hardware and model yet

Other quantizations on the Arc B580

Qwen2.5 14B Instruct on Arc B580 + 64 GB RAM · 8K context
Qwen2.5 14B Instruct Q8_08K~17.8 GB · 2.5–5.5 tok/s estimateCPU/GPU offload
Qwen2.5 14B Instruct Q6_K8K~14.3 GB · 5–10 tok/s estimateCPU/GPU offload
Qwen2.5 14B Instruct Q5_K_M8K~12.8 GB · 8–16 tok/s estimateCPU/GPU offload
Qwen2.5 14B Instruct Q4_K_M8K~11.3 GB · 18–27 tok/s estimateCompatible with limits
Qwen2.5 14B Instruct IQ4_XS8K~10.4 GB · 19–30 tok/s estimateCompatible
Qwen2.5 14B Instruct Q3_K_M8K~9.7 GB · 21–33 tok/s estimateExcellent

Alternatives

GPUs that run Qwen2.5 14B Instruct Q4_K_M entirely in VRAM

Other models that fit the Arc B580

Where to buy a Arc B580

Prices and links follow the market you choose.

Intel Arc B580

12 GB GDDR6 · 456 GB/s · 190 W

Compatible with limitsRuns Qwen2.5 14B Instruct Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

No current offer imported for this market: the link opens a marketplace search.

Frequently asked questions

Can the Arc B580 run Qwen2.5 14B Instruct?
The model needs about 11.3 GB (up to 11.9 GB) for 11.6 GB available: it fits, but with almost no margin. Use a shorter context or a smaller quantization if loading fails.
Which quantization should I use on the Arc B580?
Q4_K_M is the highest-precision quantization that fits entirely in VRAM at 8K context. ~11.3 GB / 11.6 GB.
What is the largest context on the Arc B580?
At Q4_K_M, about 9K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is Qwen2.5 14B Instruct (Arc B580)?
We estimate 18–27 tok/s (estimate, confidence low). Based on: memory bandwidth (456 GB/s) and model size.