Yes — with 5.5 GB to spare

Llama 3.2 1B Instruct at Q4_K_M fits your Radeon RX 6600 XT entirely on the GPU at 8K context, at an estimated 222 tokens per second. There is room for its full 128K window.

Fully on GPU 8K context Q4_K_M · 0.7 GB Llama 3.2 Community Released Sep 2024

The smallest Llama worth running. Fits anywhere, including phones and 4 GB cards.

Hardware requirements What hardware do I need to run Llama 3.2 1B Instruct? →

At Q4_K_M with an 8K context: a 6 GB GPU (RTX 3060 Laptop) or a 8 GB Mac (M3). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 0.7 GB
Weights 0.7 GB KV cache @ 8K 0.25 GB Runtime overhead 0.6 GB Free 5.5 GB of 7.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 2.3 GB 3.2 GB 128K 67 Reference Long context
Q8_0 1.2 GB 2.1 GB 128K 126 −0.1% ppl Long context
Q6_K 0.9 GB 1.8 GB 128K 164 −0.4% ppl Long context
Q5_K_M 0.8 GB 1.7 GB 128K 189 −0.8% ppl Long context
Q4_K_M 0.7 GB 1.5 GB 128K 222 −1.9% ppl Recommended
Q3_K_M 0.6 GB 1.4 GB 128K 275 −5.4% ppl Long context
Q2_K 0.5 GB 1.3 GB 128K 320 −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
$ ollama pull llama3.2:1b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run llama3.2:1b

The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.

01Download is 0.7 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.
03There is room to go to the model's full 128K context on this card.
See all models for this rig Compare with another model

Related models on a Radeon RX 6600 XT

ModelTotalTok/s est.
Llama 3.2 3B Instruct
3.21B · same family
Q4_K_M · 3.3 GB 86 Runs great
Llama 3.1 8B Instruct
8.03B · same family
Q4_K_M · 6.1 GB 34 Tight fit
Llama 3.3 70B Instruct
70.6B · same family
Q4_K_M · 42.8 GB ~1.0 CPU offload
Llama 4 Scout 109B-A17B
109B MoE · same family
Q4_K_M · 63.4 GB ~1.6 CPU offload
Gemma 3 1B
1.0B · similar size
Q4_K_M · 1.2 GB 276 Runs great
Qwen3 1.7B
1.72B · similar size
Q4_K_M · 2.4 GB 160 Runs great
Qwen3.5 0.8B
0.87B · similar size
Q4_K_M · 1.2 GB 317 Runs great

Every model against the Radeon RX 6600 XT →

Llama 3.2 1B Instruct on other hardware

DeviceTotalTok/s est.
GeForce RTX 3060 Laptop
5.3 GB usable · 336 GB/s
1.5 GB 292 Runs great
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
1.5 GB 222 Runs great
M3 · 8 GB
5.4 GB usable · 100 GB/s
1.5 GB 80 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
1.5 GB 313 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
1.5 GB 96 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
1.5 GB 875 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
1.5 GB 834 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
1.5 GB 321 Runs great

All 114 devices, by tier →