Yes — with 89.9 GB to spare

Llama 3.1 8B Instruct at Q4_K_M fits your Ryzen AI Max+ 395 · 128 GB entirely in unified memory at 8K context, at an estimated 32 tokens per second. There is room for its full 128K window.

Fully in unified memory 8K context Q4_K_M · 4.5 GB Llama 3.1 Community Released Jul 2024

Still the most widely deployed local model, with the largest fine-tune ecosystem. Not the strongest 8B any more.

What hardware do I need for Llama 3.1 8B Instruct? →

The VRAM budget

weights 4.5 GB
Weights 4.5 GB KV cache @ 8K 1.00 GB Runtime overhead 0.6 GB Free 89.9 GB of 96.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 15.0 GB 16.6 GB 128K 9.6 Reference Long context
Q8_0 7.9 GB 9.5 GB 128K 18 −0.1% ppl Long context
Q6_K 6.1 GB 7.7 GB 128K 23 −0.4% ppl Long context
Q5_K_M 5.3 GB 6.9 GB 128K 27 −0.8% ppl Long context
Q4_K_M 4.5 GB 6.1 GB 128K 32 −1.9% ppl Recommended
Q3_K_M 3.7 GB 5.3 GB 128K 39 −5.4% ppl Long context
Q2_K 3.1 GB 4.7 GB 128K 46 −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 llama3.1:8b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run llama3.1:8b

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

01Download is 4.5 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02macOS caps what the GPU may wire down at about 96.0 GB of 128 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
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