Skip to content
Run LLM Locally

Gemma 3 12B IT on the Arc B580

With 12 GB of VRAM, the Arc B580 runs Gemma 3 12B IT at Q4_K_M entirely on the GPU with an 8K context (about 9.1 GB needed). At Q8_0 it does not fit in VRAM.

ShareFacebookXWhatsAppLinkedInEmail

Gemma 3 12B IT

Q4_K_M · 8K context

Excellent

The model needs about 9.1 GB and fits in the 11.6 GB available, with 2.5 GB to spare.

Your hardware
Arc B580 12 GB · 64 GB RAM
Estimated memory
~9.1 GB estimate
VRAM (usable memory)
11.6 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
22–35 tok/s estimate
Largest context in fast memory
46K tokens
Confidence: low

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

Memory breakdown

~9.1 GB (8.5 GB–9.7 GB) needed · estimate

Fits entirely in VRAM · 2.5 GB left

  • Model weights6.8 GB
  • KV cache0.8 GB
  • Runtime overhead1.1 GB
  • Safety margin0.4 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (SYCL) · flash attention on · weights = real file size · sliding-window layers keep 1,024 tokens

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

Gemma 3 12B IT on Arc B580 + 64 GB RAM · 8K context
Gemma 3 12B IT Q8_08K~14.2 GB · 5–10 tok/s estimateCPU/GPU offload
Gemma 3 12B IT Q6_K8K~11.4 GB · 17–27 tok/s estimateCompatible with limits
Gemma 3 12B IT Q5_K_M8K~10.2 GB · 20–30 tok/s estimateCompatible
Gemma 3 12B IT Q4_K_M8K~9.1 GB · 22–35 tok/s estimateExcellent
Gemma 3 12B IT IQ4_XS8K~8.4 GB · 25–39 tok/s estimateExcellent
Gemma 3 12B IT Q3_K_M8K~7.8 GB · 27–42 tok/s estimateExcellent

Alternatives

GPUs that run Gemma 3 12B IT 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

ExcellentRuns Gemma 3 12B IT 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 Gemma 3 12B IT?
The model needs about 9.1 GB and fits in the 11.6 GB available, with 2.5 GB to spare.
Which quantization should I use on the Arc B580?
Q6_K is the highest-precision quantization that fits entirely in VRAM at 8K context. ~11.4 GB / 11.6 GB.
What is the largest context on the Arc B580?
At Q4_K_M, about 46K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is Gemma 3 12B IT (Arc B580)?
We estimate 22–35 tok/s (estimate, confidence low). Based on: memory bandwidth (456 GB/s) and model size.