Can MI300X 192GB run Llama-3.1-8B-Instruct?

AMD · 192 GB HBM3 · 5300 GB/s bandwidth · Meta · 8.0B · model ctx up to 128K

Yes — the MI300X 192GB (192 GB HBM3) can run Llama-3.1-8B-Instruct. At Q4 with the default 8K context it needs ≈ 7.0 GB VRAM (weights 4.4 GB + KV cache 1.6 GB + 1 GB runtime overhead), which fits within 192 GB. Decode at Q4/8K: ≈ 421.6 tok/s (estimated, batch 1). FP16 (≈ 18.6 GB) also fits, at ≈ 320.0 tok/s (measured). Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.

Fit & speed by quant and context

Quant	Context	VRAM needed	Fits?	tok/s (decode)
Q4	4K	6.2 GB	Yes	421.6 est.
Q4	8K default	7.0 GB	Yes	421.6 est.
Q4	32K	11.8 GB	Yes	421.6 est.
FP16	4K	17.8 GB	Yes	320.0 measured
FP16	8K default	18.6 GB	Yes	320.0 measured
FP16	32K	23.4 GB	Yes	320.0 measured

Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

Quant	Weights	KV cache	Overhead	Total needed	MI300X 192GB VRAM
Q4	4.4 GB	1.6 GB	1 GB	7.0 GB	192 GB
FP16	16.0 GB	1.6 GB	1 GB	18.6 GB	192 GB

Other GPUs that run Llama-3.1-8B-Instruct

• B200 192GB SXM — ≈636.4 tok/s Q4 est.
• H200 141GB SXM5 — ≈381.8 tok/s Q4 est.
• H100 80GB SXM5 — ≈266.5 tok/s Q4 est.
• Gaudi 3 128GB — ≈260.6 tok/s Q4 est.
• RTX 5090 32GB — ≈214.3 tok/s Q4 measured
• A100 80GB SXM4 — ≈162.2 tok/s Q4 est.
• RTX 6000 Ada 48GB — ≈138.6 tok/s Q4 measured
• RTX 5080 16GB — ≈136.2 tok/s Q4 measured

All GPUs for Llama-3.1-8B-Instruct →

Other models for the MI300X 192GB

• Qwen3-0.6B — ≈4215.9 tok/s Q4 est.
• gemma-3-1b-it — ≈3372.7 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈2810.6 tok/s Q4 est.
• Qwen3-1.7B — ≈1686.4 tok/s Q4 est.
• Qwen3-30B-A3B — ≈1124.2 tok/s Q4 est.
• Qwen3-Coder-30B-A3B-Instruct — ≈1124.2 tok/s Q4 est.
• GLM-4.7-Flash — ≈1124.2 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈1124.2 tok/s Q4 est.

All models on the MI300X 192GB →