Llama

Llama 3.1 8B Instruct

The Llama 3.1 model card lists an 8B model. This page uses that size class, not a separate counted total.

Llama 3.1 Community License · 8B · context 131,072

The model card says 128k context. The public config mirror has max_position_embeddings 131072.

From the model card

Strengths

  • The Llama 3.1 card describes an instruct model for dialogue, with tool use and a 128k context.
  • The card lists eight languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.

Weaknesses

  • The license requires attribution and has a monthly-active-user clause. It is not Apache-2.0.
  • The card says the knowledge cutoff is December 2023. The model is text only.
  • No Frankenstein row yet. This page does not copy Meta's benchmark table.

Sources: Llama 3.1 model card · config.json (public mirror; official weights are gated)

Memory at 8,192 tokens

Computed, not measured. Weights use llama.cpp’s whole-file averages (Q4_K_M = 4.8944 bits/weight, Q8_0 = 8.5008) on the total parameter count. KV is fp16 and does not depend on the quant. The formula, including the sliding-window and latent-KV cases, is on the methodology page.

Computed memory for Llama 3.1 8B Instruct at 8192 context
Q4_K_MQ8_0
Weights4.56 GiB7.92 GiB
KV at 8,1921 GiB1 GiB
Total5.56 GiB Computed8.92 GiB Computed

32 layers, 8 KV heads, head dim 128. Every layer stores the full context.

Tokens per second

Not yet measured. This lab has no Frankenstein row for Llama 3.1 8B Instruct, so there is no estimated tok/s either.

Hardware tiers

Minimum is the smallest RAM that holds Q4_K_M plus 8k KV. Suggested does not name a second machine or a speed this lab has not run. Performance means a CUDA-class card with 12 GB or more of GDDR6 or GDDR6X and the weights fully on the card. The Tesla P40 is 24 GB of GDDR5, so a P40 speed is not the performance-tier number.

TierExample hardwareQuantFittok/s
MinimumCPU-only, with at least 7.56 GiB of system RAM for the Q4_K_M weights, 8k KV, and a 2 GiB planning allowance.Q4_K_MCPU-only, if the RAM is thereCPU: not yet measured
SuggestedA machine you are willing to wait on, or a GPU that can hold the quant. This lab has not measured a separate “comfortable” machine, so this row does not invent one.Q4_K_M until a Q8 run existsWhichever of the machines above actually holds the weightsnot yet measured
PerformanceA CUDA-class card with 12 GB or more of GDDR6 or GDDR6X, weights fully on the card.Q4_K_MFull VRAM on a 12 GB or larger GDDR6-class cardnot yet measured

Where it sits

Best-for is a judgment from the card’s stated jobs and the model’s size. It is not a speed ranking. The matching build is Family server. Score it against a machine you have on What can my rig run?