Llama 3.3 70B Instruct vs Qwen2 72B Instruct
Llama 3.3 70B Instruct leads llmrun Score 79.7 to 77.5 (ranges overlap); neither fits 24 GB.
Model A · Meta
Llama 3.3 70B Instruct70.6B · 128K context · llama3.3 · Nov 2024
Choose Llama 3.3 70B Instruct if you want…
Higher llmrun Score
79.7 vs 77.5, ranges overlap
Ahead on the benchmarks
4 of 4 shared boards
Longer context window
128K vs 32K tokens
Also does function-calling
Qwen2 72B Instruct doesn't list it
Newer release
Nov 2024 vs May 2024
Qwen2 72B 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 3.3 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
Qwen2 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
12 GB
RTX 3060 12GB · 12 GB tier
Llama 3.3 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
Qwen2 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Llama 3.3 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
Qwen2 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
24 GBreference
RTX 4090 · 24 GB tier
Llama 3.3 70B Instruct
Doesn't fit
smallest quant needs 26.1 GB
Qwen2 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
32 GB
RTX 5090 · 32 GB tier
Llama 3.3 70B Instruct
IQ2_M · ~45 tok/s
30.9 GB · up to 16K
Qwen2 72B Instruct
IQ2_M · ~46 tok/s
30.2 GB · up to 16K
48 GB
RTX A6000 · 48 GB tier
Llama 3.3 70B Instruct
Q4_K_M · ~11 tok/stight
51.3 GB · up to 4K
Qwen2 72B Instruct
Q4_K_M · ~11 tok/stight
49.3 GB · up to 8K
Mac 32 GB
Mac Mini M4 · Macs
Llama 3.3 70B Instruct
IQ2_XS · ~4 tok/s
28 GB · up to 16K
Qwen2 72B Instruct
IQ2_S · ~4 tok/s
28.4 GB · up to 16K
Mac 64 GB
Mac Studio M4 Max · Macs
Llama 3.3 70B Instruct
Q4_K_M · ~8 tok/s
51.3 GB · up to 32K
Qwen2 72B Instruct
Q4_K_M · ~9 tok/s
49.3 GB · up to 32Kfaster
Mac 128 GB
Mac Studio M4 Max · Macs
Llama 3.3 70B Instruct
Q4_K_M · ~8 tok/s
51.3 GB · up to 128K
Qwen2 72B Instruct
Q4_K_M · ~9 tok/s
49.3 GB · up to 32Kfaster
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Llama 3.3 70B Instruct
Qwen2 72B Instruct
Coding
Llama 3.3 70B Instruct
Qwen2 72B Instruct
no data
Science
Llama 3.3 70B Instruct
Qwen2 72B Instruct
no data
Reasoning
Llama 3.3 70B Instruct
Qwen2 72B Instruct
no data
Llama 3.3 70B Instruct · #84 of 100 open models · #34 of 49 that fit ≤64 GB
Qwen2 72B Instruct · #88 of 100 open models · #38 of 49 that fit ≤64 GB
Benchmarks
4 shared boards: Llama 3.3 70B Instruct leads 4, Qwen2 72B Instruct leads 0 · Benchmarks imported Oct 2026
Llama 3.3 70B Instruct
47.4%#60/98 open
IndependentEpoch AI · Dec 2024
Qwen2 72B Instruct
40.8%#69/98 open
IndependentEpoch AI · Jun 2024
Llama 3.3 70B Instruct
65.9%#44/145 open
IndependentTIGER-Lab
Qwen2 72B Instruct
64.4%#49/145 open
IndependentTIGER-Lab
Llama 3.3 70B Instruct
41.6%#20/39 open
IndependentEpoch AI · Dec 2024
Qwen2 72B Instruct
39.1%#22/39 open
IndependentEpoch AI · Jun 2024
Llama 3.3 70B Instruct
14.4%#42/46 open
IndependentEpoch AI · Dec 2024
Qwen2 72B Instruct
11.3%#43/46 open
IndependentEpoch AI · Jun 2024
12 more boards (other shared and single-model boards)
Llama 3.3 70B Instruct
1318.1#95/187 open
ArenaLMArena · Oct 2026
Qwen2 72B Instruct
1261.9#126/187 open
ArenaLMArena · Oct 2026
Llama 3.3 70B Instruct
86.3%#2/85 open
Lab-reportedEpoch AI · Dec 2024
Qwen2 72B Instruct
82.4%#8/85 open
Lab-reportedEpoch AI · Jun 2024
Only Llama 3.3 70B Instruct (9)
- AIME 2024/20255.1%
- SciCode26.0%
- SimpleBench19.9%
- BALROG23.0%
- CritPt0.0%
- DTBench59.5%
- Fiction.LiveBench33.3%
- ForecastBench58.6
- LMCA17.5%
Only Qwen2 72B Instruct (1)
- METR Time Horizons29.9%
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 3.3 70B Instruct
33.0 GB26.4 GB file
32K 43.1 GB · 128K 75.5 GB
Qwen2 72B Instruct
31.9 GB29.8 GB file
32K 41.9 GB · 128K —
Q3_K_S
Llama 3.3 70B Instruct
34.0 GB30.9 GB file
32K 44.1 GB · 128K 76.4 GB
Qwen2 72B Instruct
32.8 GB34.5 GB file
32K 42.9 GB · 128K —
Q3_K_M
Llama 3.3 70B Instruct
37.8 GB34.3 GB file
32K 48.0 GB · 128K 80.3 GB
Qwen2 72B Instruct
36.4 GB37.7 GB file
32K 46.5 GB · 128K —
Q4_0
Llama 3.3 70B Instruct
38.8 GB40.1 GB file
32K 48.9 GB · 128K 81.3 GB
Qwen2 72B Instruct
37.3 GB41.4 GB file
32K 47.4 GB · 128K —
Q4_K_M
Llama 3.3 70B Instruct
46.6 GB42.5 GB file
32K 56.7 GB · 128K 89.1 GB
Qwen2 72B Instruct
44.6 GB47.4 GB file
32K 54.7 GB · 128K —
Q5_K_M
Llama 3.3 70B Instruct
55.3 GB49.9 GB file
32K 65.4 GB · 128K 97.8 GB
Qwen2 72B Instruct
52.8 GB54.4 GB file
32K 62.8 GB · 128K —
Q6_K
Llama 3.3 70B Instruct
64.0 GB57.9 GB file
32K 74.2 GB · 128K 107 GB
Qwen2 72B Instruct
61.0 GB64.3 GB file
32K 71.0 GB · 128K —
Q8_0
Llama 3.3 70B Instruct
77.6 GB75.0 GB file
32K 87.7 GB · 128K 120 GB
Qwen2 72B Instruct
73.7 GB77.3 GB file
32K 83.8 GB · 128K —
19 more quants
IQ2_XXS
Llama 3.3 70B Instruct
21.3 GB19.4 GB file
32K 31.5 GB · 128K 63.8 GB
Qwen2 72B Instruct
21.0 GB25.5 GB file
32K 31.0 GB · 128K —
IQ2_XS
Llama 3.3 70B Instruct
23.3 GB21.1 GB file
32K 33.4 GB · 128K 65.8 GB
Qwen2 72B Instruct
22.8 GB27.1 GB file
32K 32.9 GB · 128K —
IQ2_S
Llama 3.3 70B Instruct
24.3 GB22.2 GB file
32K 34.4 GB · 128K 66.7 GB
Qwen2 72B Instruct
23.7 GB27.9 GB file
32K 33.8 GB · 128K —
IQ2_M
Llama 3.3 70B Instruct
26.2 GB24.3 GB file
32K 36.3 GB · 128K 68.7 GB
Qwen2 72B Instruct
25.5 GB29.3 GB file
32K 35.6 GB · 128K —
IQ3_XXS
Llama 3.3 70B Instruct
30.1 GB27.7 GB file
32K 40.2 GB · 128K 72.6 GB
Qwen2 72B Instruct
29.1 GB31.8 GB file
32K 39.2 GB · 128K —
Q2_K_S
Llama 3.3 70B Instruct
31.0 GB24.5 GB file
32K 41.2 GB · 128K 73.5 GB
Qwen2 72B Instruct
not listed
IQ3_XS
Llama 3.3 70B Instruct
32.0 GB29.3 GB file
32K 42.1 GB · 128K 74.5 GB
Qwen2 72B Instruct
31.0 GB32.8 GB file
32K 41.0 GB · 128K —
IQ3_S
Llama 3.3 70B Instruct
33.0 GB30.9 GB file
32K 43.1 GB · 128K 75.5 GB
Qwen2 72B Instruct
31.9 GB34.5 GB file
32K 41.9 GB · 128K —
IQ3_M
Llama 3.3 70B Instruct
34.9 GB31.9 GB file
32K 45.0 GB · 128K 77.4 GB
Qwen2 72B Instruct
33.7 GB35.5 GB file
32K 43.8 GB · 128K —
Q3_K_L
Llama 3.3 70B Instruct
39.8 GB37.1 GB file
32K 49.9 GB · 128K 82.3 GB
Qwen2 72B Instruct
38.2 GB39.5 GB file
32K 48.3 GB · 128K —
IQ4_XS
Llama 3.3 70B Instruct
41.7 GB37.9 GB file
32K 51.8 GB · 128K 84.2 GB
Qwen2 72B Instruct
40.1 GB39.7 GB file
32K 50.1 GB · 128K —
IQ4_NL
Llama 3.3 70B Instruct
43.7 GB40.1 GB file
32K 53.8 GB · 128K 86.2 GB
Qwen2 72B Instruct
not listed
Q4_1
Llama 3.3 70B Instruct
43.7 GB44.3 GB file
32K 53.8 GB · 128K 86.2 GB
Qwen2 72B Instruct
not listed
Q4_K_S
Llama 3.3 70B Instruct
43.7 GB40.3 GB file
32K 53.8 GB · 128K 86.2 GB
Qwen2 72B Instruct
41.9 GB43.9 GB file
32K 51.9 GB · 128K —
Q4_K_L
Llama 3.3 70B Instruct
47.5 GB43.3 GB file
32K 57.7 GB · 128K 90.0 GB
Qwen2 72B Instruct
not listed
Q5_0
Llama 3.3 70B Instruct
48.5 GB48.7 GB file
32K 58.6 GB · 128K 91.0 GB
Qwen2 72B Instruct
46.4 GB50.2 GB file
32K 56.5 GB · 128K —
Q5_K_S
Llama 3.3 70B Instruct
53.4 GB48.7 GB file
32K 63.5 GB · 128K 95.9 GB
Qwen2 72B Instruct
51.0 GB51.4 GB file
32K 61.0 GB · 128K —
Q5_K_L
Llama 3.3 70B Instruct
56.3 GB50.6 GB file
32K 66.4 GB · 128K 98.8 GB
Qwen2 72B Instruct
not listed
BF16
Llama 3.3 70B Instruct
155 GB141.1 GB file
32K 165 GB · 128K 198 GB
Qwen2 72B Instruct
146 GB~145.4 GB file
32K 156 GB · 128K —
Llama 3.3 70B Instruct
Ollama · Q4_K_M
ollama run hf.co/MaziyarPanahi/Llama-3.3-70B-Instruct-GGUF:Q4_K_MQwen2 72B Instruct
Ollama · Q4_K_M
ollama run hf.co/mradermacher/Qwen2-72B-Instruct-i1-GGUF:Q4_K_M| Spec | Llama 3.3 70B Instruct | Qwen2 72B Instruct |
|---|---|---|
| Publisher | Meta | Alibaba |
| Parameters | 70.6B | 72.7B |
| Architecture | — | Qwen2ForCausalLM |
| Context | 128K tokens | 32K tokens |
| Modalities | Chat, Function-calling | Chat |
| License | llama3.3 | Other |
| Released | Nov 2024 | May 2024 |
Frequently Asked Questions
Which is better, Llama 3.3 70B Instruct or Qwen2 72B Instruct?
Llama 3.3 70B Instruct leads llmrun Score 79.7 to 77.5 (ranges overlap); neither fits 24 GB. Choose Llama 3.3 70B Instruct for higher llmrun Score and ahead on the benchmarks.
Which needs less VRAM, Llama 3.3 70B Instruct or Qwen2 72B Instruct?
At Q4_K_M, Llama 3.3 70B Instruct requires 46.6 GB while Qwen2 72B Instruct needs 44.6 GB, making Qwen2 72B Instruct the easier model to run on your local setup.
Can I run Llama 3.3 70B Instruct or Qwen2 72B Instruct on a 16 GB GPU?
Llama 3.3 70B Instruct does not fit (smallest quant needs 26.1 GB); Qwen2 72B Instruct does not fit (smallest quant needs 25.7 GB).
Which has a longer context window, Llama 3.3 70B Instruct or Qwen2 72B Instruct?
Llama 3.3 70B Instruct supports 131,072 tokens and Qwen2 72B Instruct supports 32,768 tokens.