Llama

Llama 3.3 70B Instruct

The Llama 3.3 model card lists a 70B instruct model. This page uses that size class, not a separate counted total.

Llama 3.3 Community License · 70B · 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 3.3 card describes a 70B instruct model with tool use and a 128k context.
  • The card presents it as improved over Llama 3.1 70B, in the same eight languages.

Weaknesses

  • Dense 70B. The weight file is the full count, and a 24 GB card does not hold Q4_K_M plus 8k KV under the formula on this site.
  • The license requires attribution and has a monthly-active-user clause. Text only.
  • No Frankenstein row yet. This page does not copy Meta's benchmark table.

Sources: Llama 3.3 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 3.3 70B Instruct at 8192 context
Q4_K_MQ8_0
Weights39.88 GiB69.27 GiB
KV at 8,1922.5 GiB2.5 GiB
Total42.38 GiB Computed71.77 GiB Computed

80 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 3.3 70B 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 44.38 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 enough GDDR6 or GDDR6X to hold about 43.38 GiB (Q4_K_M weights, 8k KV, and a 1 GiB planning allowance). 12 GB is not enough for that total.Q4_K_MFull VRAM only if the card is larger than 12 GBnot 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 CPU-only used Xeon. Score it against a machine you have on What can my rig run?