Llama on NVIDIA Blackwell

Can I run Llama 3.1 8B on an RTX 5070 Ti?

Yes. Llama 3.1 8B at Q4_K_M uses 6.4 GB of the 14.2 GB available on a RTX 5070 Ti, and runs at about 113 tokens per second. You can push the context to 70K.

Runs comfortably

6.4 GB of 14.2 GB · 45%
014 GB
Weights 4.6 GB
KV cache 1.0 GB
Runtime overhead 0.8 GB

Llama 3.1 8B at Q4_K_M leaves 7.8 GB spare on a RTX 5070 Ti. There is room to raise the context length or move up a quantisation level.

Generation113tok/s
Prompt processing2301tok/s
Max context70Ktokens
KV per 1K tokens0GB

Every quantisation of Llama 3.1 8B on a RTX 5070 Ti

Highlighted row is the highest quality that still fits at 8K context.

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 15.0 GB 16.8 GB Won't fit — 11.1
INT8 / W8A8 8.50 7.7 GB 9.5 GB Runs comfortably 46K 71.2
Q8_0 (GGUF) 8.50 7.7 GB 9.5 GB Runs comfortably 46K 71.2
FP8 (E4M3) 8.00 7.5 GB 9.3 GB Runs comfortably 48K 73.2
Q6_K 6.56 6.1 GB 8.0 GB Runs comfortably 58K 87.8
AWQ 4-bit 4.25 5.4 GB 7.2 GB Runs comfortably 64K 98.3
GPTQ 4-bit 4.25 5.4 GB 7.2 GB Runs comfortably 64K 98.3
MXFP4 4.25 5.4 GB 7.2 GB Runs comfortably 64K 98.3
Q5_K_M 5.67 5.3 GB 7.1 GB Runs comfortably 65K 100
Q5_K_S 5.52 5.2 GB 7.0 GB Runs comfortably 66K 103
Q4_K_M 4.85 4.6 GB 6.4 GB Runs comfortably 70K 113
Q4_K_S 4.58 4.4 GB 6.2 GB Runs comfortably 72K 118
Q4_0 4.55 4.4 GB 6.2 GB Runs comfortably 72K 119
IQ4_XS 4.25 4.1 GB 5.9 GB Runs comfortably 74K 125
Q3_K_M 3.91 3.8 GB 5.7 GB Runs comfortably 77K 133
IQ3_M 3.70 3.7 GB 5.5 GB Runs comfortably 78K 138
IQ3_XXS 3.06 3.2 GB 5.0 GB Runs comfortably 82K 157
Q2_K 2.63 2.8 GB 4.6 GB Runs comfortably 85K 173
IQ2_XXS 2.06 2.3 GB 4.2 GB Runs comfortably 89K 200
IQ1_M 1.75 2.1 GB 3.9 GB Runs comfortably 91K 219

Also worth checking

Llama 3.1 8B on every GPU
Full hardware tableEverything that runs on a RTX 5070 Ti
Full model tableWhy the KV cache is the part that bites
Guide