TokenAssemble

Can an Intel Arc A770 16 GB run Qwen2.5-1.5B-Instruct?

Yes. Qwen2.5-1.5B-Instruct needs 2.29GB at Q8_0 with llama.cpp and 8K context; the Intel Arc A770 16 GB has 16GB of VRAM (15.5GB usable) — grade A+, with decode speed in the interactive tier.

Intel Arc A770 16 GB · Qwen2.5-1.5B-Instruct · Q8_0

Fits — grade A+

InteractivebetaROCm/Vulkan performance not yet calibrated
weights 1.65 GBKV cache 0.23 GBoverhead 0.40 GBpool 15.5 GBneeds 2.29 GB

assumes llama.cpp · batch 1 · 8K context · fp16 KV cache

$349 MSRP · as of 2026-07-08

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

Every quant, graded

Intel Arc A770 16 GB × Qwen2.5-1.5B-Instruct, llama.cpp, 8K context.

QuantFile sizeFitSpeed tier
Q8_01.6 GBFits · A+interactive · beta
Q6_K1.3 GBFits · A+interactive · beta
Q5_K_M1.1 GBFits · A+interactive · beta
Q4_K_M1.0 GBFits · A+interactive · beta

Qwen2.5-1.5B-Instruct on similar hardware

More models on the Intel Arc A770 16 GB

Verdict computed from published specs and measured GGUF file sizes — see how the math works.