Yes, just — 0.7 GB spare

Qwen3 8B at Q4_K_M fits your Arc A750 entirely on the GPU at 8K context, at an estimated 67 tokens per second. Past 12K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully on GPU 8K context Q4_K_M · 4.6 GB Apache 2.0 Released Apr 2025

Apache-2.0 alternative to Llama 3.1 8B, with a switchable thinking mode.

Hardware requirements What hardware do I need to run Qwen3 8B? →

At Q4_K_M with an 8K context: a 10 GB GPU (Arc B570) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 4.6 GB
Weights 4.6 GB KV cache @ 8K 1.13 GB Runtime overhead 0.6 GB Free 0.7 GB of 7.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 15.3 GB 17.0 GB — ~3.4 Reference 10.0 GB over
Q8_0 8.1 GB 9.8 GB — ~11 −0.1% ppl 2.8 GB over
Q6_K 6.3 GB 8.0 GB 1K ~23 −0.4% ppl 1.0 GB over
Q5_K_M 5.4 GB 7.1 GB 7K ~48 −0.8% ppl 0.1 GB over
Q4_K_M 4.6 GB 6.3 GB 12K 67 −1.9% ppl Recommended
Q3_K_M 3.7 GB 5.5 GB 19K 83 −5.4% ppl Long context
Q2_K 3.2 GB 4.9 GB 22K 97 −15% ppl Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

terminal
$ llama-server \
    -hf Qwen/Qwen3-8B:Q4_K_M \
    -c 8192 -ngl 99

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 4.6 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03Only 0.7 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 12K context.
See all models for this rig Compare with another model

Related models on an Arc A750

ModelTotalTok/s est.
Qwen3 14B
14.8B · same family
Q4_K_M · 10.2 GB ~9.6 CPU offload
Qwen3 4B
4.02B · same family
Q4_K_M · 4.0 GB 137 Runs great
Qwen3 30B-A3B
30.5B MoE · same family
Q4_K_M · 18.5 GB ~11 CPU offload
Qwen3 Coder 30B-A3B
30.5B MoE · same family
Q4_K_M · 18.5 GB ~11 CPU offload
Fara 7B
8.29B · similar size
Q4_K_M · 5.7 GB 66 Runs great
Llama 3.1 8B Instruct
8.03B · similar size
Q4_K_M · 6.1 GB 69 Tight fit
Gemma 4 E4B
8.0B · similar size
Q4_K_M · 5.2 GB 69 Runs great

Every model against the Arc A750 →

Qwen3 8B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
6.3 GB 34 Tight fit
Arc B570
8.8 GB usable · 380 GB/s
6.3 GB 50 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
6.3 GB 47 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
6.3 GB 15 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
6.3 GB 133 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
6.3 GB 126 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
6.3 GB 49 Runs great

All 114 devices, by tier →