Llama 3.1 70B Instruct vs Llama 3.3 70B Instruct
Llama 3.1 70B Instruct and Llama 3.3 70B Instruct match in llmrun Score, with values of 77.9 versus 79.7; neither fits 24 GB.
Model A · Meta
Llama 3.1 70B Instruct70.6B · 128K context · Llama 3.1 Community · Jul 2024
Model B · Meta
Llama 3.3 70B Instruct70.6B · 128K context · llama3.3 · Nov 2024
Choose Llama 3.3 70B Instruct if you want…
Ahead on the benchmarks
6 of 8 shared boards
Newer release
Nov 2024 vs Jul 2024
Llama 3.1 70B Instruct: no clear edge over Llama 3.3 70B Instruct in the data we have.
On your hardware
Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.
8 GB
RTX 4060 · 8 GB tier
Llama 3.1 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
Llama 3.3 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
12 GB
RTX 3060 12GB · 12 GB tier
Llama 3.1 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
Llama 3.3 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Llama 3.1 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
Llama 3.3 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
24 GBreference
RTX 4090 · 24 GB tier
Llama 3.1 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
Llama 3.3 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
32 GB
RTX 5090 · 32 GB tier
Llama 3.1 70B Instruct
IQ2_M · ~45 tok/s
30.9 GB · up to 16K
Llama 3.3 70B Instruct
IQ2_M · ~45 tok/s
30.9 GB · up to 16K
48 GB
RTX A6000 · 48 GB tier
Llama 3.1 70B Instruct
Q4_K_M · ~11 tok/stight
51.3 GB · up to 4K
Llama 3.3 70B Instruct
Q4_K_M · ~11 tok/stight
51.3 GB · up to 4K
Mac 32 GB
Mac Mini M4 · Macs
Llama 3.1 70B Instruct
IQ2_XS · ~4 tok/s
28 GB · up to 16K
Llama 3.3 70B Instruct
IQ2_XS · ~4 tok/s
28 GB · up to 16K
Mac 64 GB
Mac Studio M4 Max · Macs
Llama 3.1 70B Instruct
Q4_K_M · ~8 tok/s
51.3 GB · up to 32K
Llama 3.3 70B Instruct
Q4_K_M · ~8 tok/s
51.3 GB · up to 32K
Mac 128 GB
Mac Studio M4 Max · Macs
Llama 3.1 70B Instruct
Q4_K_M · ~8 tok/s
51.3 GB · up to 128K
Llama 3.3 70B Instruct
Q4_K_M · ~8 tok/s
51.3 GB · up to 128K
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Llama 3.1 70B Instruct
Llama 3.3 70B Instruct
Coding
Llama 3.1 70B Instruct
no data
Llama 3.3 70B Instruct
Science
Llama 3.1 70B Instruct
no data
Llama 3.3 70B Instruct
Reasoning
Llama 3.1 70B Instruct
Llama 3.3 70B Instruct
Llama 3.1 70B Instruct · #87 of 100 open models · #37 of 49 that fit ≤64 GB
Llama 3.3 70B Instruct · #84 of 100 open models · #34 of 49 that fit ≤64 GB
Benchmarks
8 shared boards: Llama 3.1 70B Instruct leads 2, Llama 3.3 70B Instruct leads 6 · Benchmarks imported Oct 2026
Llama 3.1 70B Instruct
44.2%#66/98 open
IndependentEpoch AI · Jul 2024
Llama 3.3 70B Instruct
47.4%#60/98 open
IndependentEpoch AI · Dec 2024
Llama 3.1 70B Instruct
3.6%#71/86 open
IndependentEpoch AI · Jul 2024
Llama 3.3 70B Instruct
5.1%#68/86 open
IndependentEpoch AI · Dec 2024
Llama 3.1 70B Instruct
62.8%#53/145 open
IndependentTIGER-Lab
Llama 3.3 70B Instruct
65.9%#44/145 open
IndependentTIGER-Lab
Llama 3.1 70B Instruct
36.7%#23/39 open
IndependentEpoch AI · Jul 2024
Llama 3.3 70B Instruct
41.6%#20/39 open
IndependentEpoch AI · Dec 2024
Llama 3.1 70B Instruct
9.0%#44/46 open
IndependentEpoch AI · Jul 2024
Llama 3.3 70B Instruct
14.4%#42/46 open
IndependentEpoch AI · Dec 2024
Llama 3.1 70B Instruct
27.9%#2/15 open
IndependentEpoch AI · Jul 2024
Llama 3.3 70B Instruct
23.0%#4/15 open
IndependentEpoch AI · Dec 2024
Llama 3.1 70B Instruct
60.0%#48/68 open
Lab-reportedEpoch AI · Jul 2024
Llama 3.3 70B Instruct
59.5%#51/68 open
Lab-reportedEpoch AI · Dec 2024
Llama 3.1 70B Instruct
14.8%#42/54 open
Lab-reportedEpoch AI · Jul 2024
Llama 3.3 70B Instruct
17.5%#36/54 open
Lab-reportedEpoch AI · Dec 2024
7 more boards (other shared and single-model boards)
Llama 3.1 70B Instruct
1293.4#109/187 open
ArenaLMArena · Oct 2026
Llama 3.3 70B Instruct
1318.1#95/187 open
ArenaLMArena · Oct 2026
Llama 3.1 70B Instruct
80.1%#10/85 open
Lab-reportedEpoch AI · Jul 2024
Llama 3.3 70B Instruct
86.3%#2/85 open
Lab-reportedEpoch AI · Dec 2024
Only Llama 3.3 70B Instruct (5)
- SciCode26.0%
- SimpleBench19.9%
- CritPt0.0%
- Fiction.LiveBench33.3%
- ForecastBench58.6
VRAM by quantization
Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.
Q2_K
Llama 3.1 70B Instruct
33.0 GB26.4 GB file
32K 43.1 GB · 128K 75.5 GB
Llama 3.3 70B Instruct
33.0 GB26.4 GB file
32K 43.1 GB · 128K 75.5 GB
Q3_K_S
Llama 3.1 70B Instruct
34.0 GB30.9 GB file
32K 44.1 GB · 128K 76.4 GB
Llama 3.3 70B Instruct
34.0 GB30.9 GB file
32K 44.1 GB · 128K 76.4 GB
Q3_K_M
Llama 3.1 70B Instruct
37.8 GB34.3 GB file
32K 48.0 GB · 128K 80.3 GB
Llama 3.3 70B Instruct
37.8 GB34.3 GB file
32K 48.0 GB · 128K 80.3 GB
Q4_0
Llama 3.1 70B Instruct
38.8 GB40.1 GB file
32K 48.9 GB · 128K 81.3 GB
Llama 3.3 70B Instruct
38.8 GB40.1 GB file
32K 48.9 GB · 128K 81.3 GB
Q4_K_M
Llama 3.1 70B Instruct
46.6 GB42.5 GB file
32K 56.7 GB · 128K 89.1 GB
Llama 3.3 70B Instruct
46.6 GB42.5 GB file
32K 56.7 GB · 128K 89.1 GB
Q5_K_M
Llama 3.1 70B Instruct
55.3 GB49.9 GB file
32K 65.4 GB · 128K 97.8 GB
Llama 3.3 70B Instruct
55.3 GB49.9 GB file
32K 65.4 GB · 128K 97.8 GB
Q6_K
Llama 3.1 70B Instruct
64.0 GB57.9 GB file
32K 74.2 GB · 128K 107 GB
Llama 3.3 70B Instruct
64.0 GB57.9 GB file
32K 74.2 GB · 128K 107 GB
Q8_0
Llama 3.1 70B Instruct
77.6 GB75.0 GB file
32K 87.7 GB · 128K 120 GB
Llama 3.3 70B Instruct
77.6 GB75.0 GB file
32K 87.7 GB · 128K 120 GB
19 more quants
IQ2_XXS
Llama 3.1 70B Instruct
21.3 GB19.1 GB file
32K 31.5 GB · 128K 63.8 GB
Llama 3.3 70B Instruct
21.3 GB19.4 GB file
32K 31.5 GB · 128K 63.8 GB
IQ2_XS
Llama 3.1 70B Instruct
23.3 GB21.1 GB file
32K 33.4 GB · 128K 65.8 GB
Llama 3.3 70B Instruct
23.3 GB21.1 GB file
32K 33.4 GB · 128K 65.8 GB
IQ2_S
Llama 3.1 70B Instruct
24.3 GB22.2 GB file
32K 34.4 GB · 128K 66.7 GB
Llama 3.3 70B Instruct
24.3 GB22.2 GB file
32K 34.4 GB · 128K 66.7 GB
IQ2_M
Llama 3.1 70B Instruct
26.2 GB24.1 GB file
32K 36.3 GB · 128K 68.7 GB
Llama 3.3 70B Instruct
26.2 GB24.3 GB file
32K 36.3 GB · 128K 68.7 GB
IQ3_XXS
Llama 3.1 70B Instruct
30.1 GB27.5 GB file
32K 40.2 GB · 128K 72.6 GB
Llama 3.3 70B Instruct
30.1 GB27.7 GB file
32K 40.2 GB · 128K 72.6 GB
Q2_K_S
Llama 3.1 70B Instruct
not listed
Llama 3.3 70B Instruct
31.0 GB24.5 GB file
32K 41.2 GB · 128K 73.5 GB
IQ3_XS
Llama 3.1 70B Instruct
32.0 GB29.3 GB file
32K 42.1 GB · 128K 74.5 GB
Llama 3.3 70B Instruct
32.0 GB29.3 GB file
32K 42.1 GB · 128K 74.5 GB
IQ3_S
Llama 3.1 70B Instruct
33.0 GB30.9 GB file
32K 43.1 GB · 128K 75.5 GB
Llama 3.3 70B Instruct
33.0 GB30.9 GB file
32K 43.1 GB · 128K 75.5 GB
IQ3_M
Llama 3.1 70B Instruct
34.9 GB31.9 GB file
32K 45.0 GB · 128K 77.4 GB
Llama 3.3 70B Instruct
34.9 GB31.9 GB file
32K 45.0 GB · 128K 77.4 GB
Q3_K_L
Llama 3.1 70B Instruct
39.8 GB37.1 GB file
32K 49.9 GB · 128K 82.3 GB
Llama 3.3 70B Instruct
39.8 GB37.1 GB file
32K 49.9 GB · 128K 82.3 GB
IQ4_XS
Llama 3.1 70B Instruct
41.7 GB37.9 GB file
32K 51.8 GB · 128K 84.2 GB
Llama 3.3 70B Instruct
41.7 GB37.9 GB file
32K 51.8 GB · 128K 84.2 GB
IQ4_NL
Llama 3.1 70B Instruct
not listed
Llama 3.3 70B Instruct
43.7 GB40.1 GB file
32K 53.8 GB · 128K 86.2 GB
Q4_1
Llama 3.1 70B Instruct
not listed
Llama 3.3 70B Instruct
43.7 GB44.3 GB file
32K 53.8 GB · 128K 86.2 GB
Q4_K_S
Llama 3.1 70B Instruct
43.7 GB40.3 GB file
32K 53.8 GB · 128K 86.2 GB
Llama 3.3 70B Instruct
43.7 GB40.3 GB file
32K 53.8 GB · 128K 86.2 GB
Q4_K_L
Llama 3.1 70B Instruct
47.5 GB43.3 GB file
32K 57.7 GB · 128K 90.0 GB
Llama 3.3 70B Instruct
47.5 GB43.3 GB file
32K 57.7 GB · 128K 90.0 GB
Q5_0
Llama 3.1 70B Instruct
48.5 GB48.7 GB file
32K 58.6 GB · 128K 91.0 GB
Llama 3.3 70B Instruct
48.5 GB48.7 GB file
32K 58.6 GB · 128K 91.0 GB
Q5_K_S
Llama 3.1 70B Instruct
53.4 GB48.7 GB file
32K 63.5 GB · 128K 95.9 GB
Llama 3.3 70B Instruct
53.4 GB48.7 GB file
32K 63.5 GB · 128K 95.9 GB
Q5_K_L
Llama 3.1 70B Instruct
56.3 GB50.6 GB file
32K 66.4 GB · 128K 98.8 GB
Llama 3.3 70B Instruct
56.3 GB50.6 GB file
32K 66.4 GB · 128K 98.8 GB
BF16
Llama 3.1 70B Instruct
155 GB~141.1 GB file
32K 165 GB · 128K 198 GB
Llama 3.3 70B Instruct
155 GB141.1 GB file
32K 165 GB · 128K 198 GB
Llama 3.1 70B Instruct
Ollama · Q4_K_M
ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q4_K_MLlama 3.3 70B Instruct
Ollama · Q4_K_M
ollama run hf.co/MaziyarPanahi/Llama-3.3-70B-Instruct-GGUF:Q4_K_M| Spec | Llama 3.1 70B Instruct | Llama 3.3 70B Instruct |
|---|---|---|
| Publisher | Meta | Meta |
| Parameters | 70.6B | 70.6B |
| Context | 128K tokens | 128K tokens |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | Llama 3.1 Community | llama3.3 |
| Released | Jul 2024 | Nov 2024 |
Frequently Asked Questions
Which is better, Llama 3.1 70B Instruct or Llama 3.3 70B Instruct?
Llama 3.1 70B Instruct and Llama 3.3 70B Instruct match in llmrun Score, with values of 77.9 versus 79.7; neither fits 24 GB. Choose Llama 3.3 70B Instruct for ahead on the benchmarks and newer release.
Which needs less VRAM, Llama 3.1 70B Instruct or Llama 3.3 70B Instruct?
At Q4_K_M, Llama 3.1 70B Instruct requires 46.6 GB while Llama 3.3 70B Instruct needs 46.6 GB, making Llama 3.1 70B Instruct the easier model to run on your local setup.
Can I run Llama 3.1 70B Instruct or Llama 3.3 70B Instruct on a 16 GB GPU?
Llama 3.1 70B Instruct does not fit (smallest quant needs 26.1 GB); Llama 3.3 70B Instruct does not fit (smallest quant needs 26.1 GB).
Which has a longer context window, Llama 3.1 70B Instruct or Llama 3.3 70B Instruct?
Llama 3.1 70B Instruct supports 131,072 tokens and Llama 3.3 70B Instruct supports 131,072 tokens.