TokenAssemble

Intel GPU

Intel Arc A770 16 GB

The Intel Arc A770 16 GB has 16GB of VRAM and 560 GB/s of memory bandwidth. Its sweet spot tops out around gpt-oss-20b — the largest model that loads cleanly at a quality quant with llama.cpp at 8K context.

Intel verdicts are beta: fit is physics and holds, but ROCm/Vulkan speed tiers aren't calibrated yet — treat tiers as provisional until real measurements land.
VRAM
16 GB
Memory bandwidth
560 GB/s
TDP
225 W
MSRP
$349
Backends
Vulkan

Also good for gaming — 1080p-class (estimated from FP32 compute, not a game benchmark)

Specs as of 2026-07-08 · source

Intel Arc A770 16 GB for local AI — common questions

How much VRAM does the Intel Arc A770 16 GB have?
The Intel Arc A770 16 GB has 16GB of VRAM with 560 GB/s of memory bandwidth. VRAM sets which models fit; bandwidth sets how fast they feel once they do.
Is the Intel Arc A770 16 GB good for running AI models locally?
Yes, within limits. 16GB comfortably runs small and mid-size models at a quality quant, but the largest open models will not fit. The largest model it loads cleanly is gpt-oss-20b, at a quality quant with llama.cpp at 8K context.
What runtimes work with the Intel Arc A770 16 GB?
It runs on Vulkan, which covers Ollama, llama.cpp and LM Studio. Runtime choice affects speed and features, not whether a model fits.

Affiliate link — we may earn a commission. Verdicts are computed before any link is attached.

What an Intel Arc A770 16 GB can run

Every model we track, graded at its best clean-fit quant. Click any verdict for the full breakdown.

ModelBest-quant verdict · llama.cpp · 8K context
Qwen3-8BFits · A · Q8_0interactivebeta
gemma-4-26B-A4B-itTight · C · MXFP4_MOEinteractive · offloadbeta
Qwen2.5-7B-InstructFits · A · Q8_0interactivebeta
Qwen2.5-1.5B-InstructFits · A · Q8_0interactivebeta
Llama-3.2-1B-InstructFits · A · Q8_0interactivebeta
Llama-3.1-8B-InstructFits · A · Q8_0interactivebeta
DeepSeek-R1Won't fitbeta
Qwen3.5-9BFits · B · Q8_0interactivebeta
gpt-oss-20bFits · B · MXFP4interactivebeta
Qwen3.6-35B-A3BTight · C · MXFP4_MOEinteractive · offloadbeta
Qwen2.5-3B-InstructFits · A · Q8_0interactivebeta
Qwen3-32BTight · C · Q4_K_Mpainful · offloadbeta
Qwen3.6-27BTight · C · Q4_K_Musable · offloadbeta
Qwen2.5-0.5B-InstructFits · A · Q8_0interactivebeta
Mistral-7B-Instruct-v0.3Fits · A · Q8_0interactivebeta
gpt-oss-120bTight · C · MXFP4interactive · offloadbeta
Qwen3-14BFits · B · Q5_K_Minteractivebeta
Qwen3-30B-A3BTight · C · Q4_K_Minteractive · offloadbeta
Qwen2.5-32B-InstructTight · C · Q4_K_Mpainful · offloadbeta
DeepSeek-V4-FlashWon't fitbeta
Qwen2.5-14B-InstructFits · B · Q5_K_Minteractivebeta
Llama-3.2-3B-InstructFits · A · Q8_0interactivebeta
gemma-3-4b-itFits · A · Q8_0interactivebeta
gemma-3-12b-itFits · B · Q6_Kinteractivebeta
Llama-3.1-70B-InstructTight · C · Q4_K_Mpainful · offloadbeta
Phi-3.5-mini-instructFits · A · Q8_0interactivebeta
Phi-4Fits · B · Q5_K_Minteractivebeta
DeepSeek-R1-Distill-Qwen-32BTight · C · Q4_K_Mpainful · offloadbeta
gemma-3-27b-itTight · C · Q4_K_Musable · offloadbeta
Llama-3.3-70B-InstructTight · C · Q4_K_Mpainful · offloadbeta
Qwen2.5-72B-InstructTight · C · Q4_K_Mpainful · offloadbeta
gemma-2-2b-itFits · A · Q8_0interactivebeta
DeepSeek-R1-Distill-Qwen-14BFits · B · Q5_K_Minteractivebeta
DeepSeek-R1-Distill-Llama-8BFits · A · Q8_0interactivebeta
DeepSeek-R1-Distill-Qwen-7BFits · A · Q8_0interactivebeta
gemma-2-9b-itFits · B · Q8_0interactivebeta
Mistral-Nemo-Instruct-2407Fits · B · Q6_Kinteractivebeta
QwQ-32BTight · C · Q4_K_Mpainful · offloadbeta
Mistral-Small-24B-Instruct-2501Tight · C · Q4_K_Musable · offloadbeta
gemma-2-27b-itTight · C · Q4_K_Musable · offloadbeta

Have a specific model in mind? Check it against the Intel Arc A770 16 GB at your own quant and context length.

Check with the Intel Arc A770 16 GB preselected →

Verdicts computed from published specs and measured GGUF sizes — how the math works.