Llama 4 Scout 17B 16E Instruct vs Qwen2.5 72B Instruct
Llama 4 Scout 17B 16E Instruct and Qwen2.5 72B Instruct match in llmrun Score, with values of 81.8 versus 81.7; neither fits 24 GB.
Model A · Meta
Llama 4 Scout 17B 16E Instruct108.6B · 17B active · Other · Apr 2025
Model B · Alibaba
Qwen2.5 72B Instruct72.7B · 32K context · Other · Sep 2024
Choose Llama 4 Scout 17B 16E Instruct if you want…
Also does vision
Qwen2.5 72B Instruct doesn't list it
Newer release
Apr 2025 vs Sep 2024
Choose Qwen2.5 72B Instruct if you want…
Fits a 48 GB GPU
Q4_K_M · 49.3 GB; Llama 4 Scout 17B 16E Instruct needs 38.2 GB at its smallest quant
Lighter on memory
44.6 vs 71.7 GB at Q4_K_M
Also does chat, function-calling
Llama 4 Scout 17B 16E Instruct doesn't list it
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 4 Scout 17B 16E Instruct
Doesn't fit
smallest quant needs 38.2 GB
Qwen2.5 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
12 GB
RTX 3060 12GB · 12 GB tier
Llama 4 Scout 17B 16E Instruct
Doesn't fit
smallest quant needs 38.2 GB
Qwen2.5 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Llama 4 Scout 17B 16E Instruct
Doesn't fit
smallest quant needs 38.2 GB
Qwen2.5 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
24 GBreference
RTX 4090 · 24 GB tier
Llama 4 Scout 17B 16E Instruct
Doesn't fit
smallest quant needs 38.2 GB
Qwen2.5 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
32 GB
RTX 5090 · 32 GB tier
Llama 4 Scout 17B 16E Instruct
Doesn't fit
smallest quant needs 38.2 GB
Qwen2.5 72B Instruct
IQ2_M · ~46 tok/s
30.2 GB · up to 16Kfits
48 GB
RTX A6000 · 48 GB tier
Llama 4 Scout 17B 16E Instruct
IQ2_M · ~65 tok/s
45.7 GB · up to 16Kmore headroom
Qwen2.5 72B Instruct
Q4_K_M · ~11 tok/stight
49.3 GB · up to 8K
Mac 32 GB
Mac Mini M4 · Macs
Llama 4 Scout 17B 16E Instruct
Doesn't fit
smallest quant needs 38.2 GB
Qwen2.5 72B Instruct
IQ2_S · ~4 tok/s
28.4 GB · up to 16Kfits
Mac 64 GB
Mac Studio M4 Max · Macs
Llama 4 Scout 17B 16E Instruct
IQ3_M · ~32 tok/s
59.1 GB · up to 16K
Qwen2.5 72B Instruct
Q4_K_M · ~9 tok/s
49.3 GB · up to 32Kmore headroom
Mac 128 GB
Mac Studio M4 Max · Macs
Llama 4 Scout 17B 16E Instruct
Q4_K_M · ~26 tok/s
77 GB · up to 32Kfaster
Qwen2.5 72B Instruct
Q4_K_M · ~9 tok/s
49.3 GB · up to 32K
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Llama 4 Scout 17B 16E Instruct
Qwen2.5 72B Instruct
Science
Llama 4 Scout 17B 16E Instruct
Qwen2.5 72B Instruct
no data
Reasoning
Llama 4 Scout 17B 16E Instruct
Qwen2.5 72B Instruct
Llama 4 Scout 17B 16E Instruct · #79 of 100 open models · #40 of 60 that fit ≤96 GB
Qwen2.5 72B Instruct · #80 of 100 open models · #30 of 49 that fit ≤64 GB
Benchmarks
7 shared boards: Llama 4 Scout 17B 16E Instruct leads 2, Qwen2.5 72B Instruct leads 4 · Benchmarks imported Oct 2026
Llama 4 Scout 17B 16E Instruct
51.8%#51/98 open
IndependentEpoch AI · Apr 2025
Qwen2.5 72B Instruct
49.1%#54/98 open
IndependentEpoch AI · Sep 2024
Llama 4 Scout 17B 16E Instruct
7.8%#62/86 open
IndependentEpoch AI · Apr 2025
Qwen2.5 72B Instruct
8.1%#60/86 open
IndependentEpoch AI · Sep 2024
Llama 4 Scout 17B 16E Instruct
74.3%#31/145 open
IndependentTIGER-Lab
Qwen2.5 72B Instruct
71.6%#35/145 open
IndependentTIGER-Lab
Llama 4 Scout 17B 16E Instruct
62.3%#12/39 open
IndependentEpoch AI · Apr 2025
Qwen2.5 72B Instruct
63.2%#11/39 open
IndependentEpoch AI · Sep 2024
Llama 4 Scout 17B 16E Instruct
57.9%#53/68 open
Lab-reportedEpoch AI · Apr 2025
Qwen2.5 72B Instruct
62.9%#40/68 open
Lab-reportedEpoch AI · Sep 2024
Llama 4 Scout 17B 16E Instruct
57.5#17/26 open
Lab-reportedEpoch AI · Apr 2025
Qwen2.5 72B Instruct
57.5#18/26 open
Lab-reportedEpoch AI · Sep 2024
Llama 4 Scout 17B 16E Instruct
12.0%#46/54 open
Lab-reportedEpoch AI · Apr 2025
Qwen2.5 72B Instruct
13.4%#44/54 open
Lab-reportedEpoch AI · Sep 2024
10 more boards (other shared and single-model boards)
Llama 4 Scout 17B 16E Instruct
1321.5#94/187 open
ArenaLMArena · Oct 2026
Qwen2.5 72B Instruct
1302.9#106/187 open
ArenaLMArena · Oct 2026
Only Llama 4 Scout 17B 16E Instruct (5)
- ARC-AGI-20.0%
- SciCode17.0%
- ARC-AGI0.5%
- CritPt0.0%
- Fiction.LiveBench36.0%
Only Qwen2.5 72B Instruct (4)
- MMLU85.3%
- WeirdML16.0%
- BALROG16.2%
- METR Time Horizons35.8%
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 4 Scout 17B 16E Instruct
50.8 GB39.6 GB file
32K 62.2 GB · 128K 98.7 GB
Qwen2.5 72B Instruct
31.9 GB29.8 GB file
32K 41.9 GB · 128K —
Q3_K_S
Llama 4 Scout 17B 16E Instruct
52.3 GB46.7 GB file
32K 63.7 GB · 128K 100 GB
Qwen2.5 72B Instruct
32.8 GB34.5 GB file
32K 42.9 GB · 128K —
Q3_K_M
Llama 4 Scout 17B 16E Instruct
58.3 GB51.8 GB file
32K 69.7 GB · 128K 106 GB
Qwen2.5 72B Instruct
36.4 GB37.7 GB file
32K 46.5 GB · 128K —
Q4_0
Llama 4 Scout 17B 16E Instruct
59.8 GB61.2 GB file
32K 71.2 GB · 128K 108 GB
Qwen2.5 72B Instruct
37.3 GB41.4 GB file
32K 47.4 GB · 128K —
Q4_K_M
Llama 4 Scout 17B 16E Instruct
71.7 GB65.4 GB file
32K 83.1 GB · 128K 120 GB
Qwen2.5 72B Instruct
44.6 GB47.4 GB file
32K 54.7 GB · 128K —
Q5_K_M
Llama 4 Scout 17B 16E Instruct
85.2 GB76.5 GB file
32K 96.6 GB · 128K 133 GB
Qwen2.5 72B Instruct
52.8 GB54.4 GB file
32K 62.8 GB · 128K —
Q6_K
Llama 4 Scout 17B 16E Instruct
98.6 GB88.4 GB file
32K 110 GB · 128K 147 GB
Qwen2.5 72B Instruct
61.0 GB64.3 GB file
32K 71.0 GB · 128K —
Q8_0
Llama 4 Scout 17B 16E Instruct
120 GB114.5 GB file
32K 131 GB · 128K 167 GB
Qwen2.5 72B Instruct
73.7 GB77.3 GB file
32K 83.8 GB · 128K —
17 more quants
IQ2_XXS
Llama 4 Scout 17B 16E Instruct
32.9 GB37.4 GB file
32K 44.3 GB · 128K 80.8 GB
Qwen2.5 72B Instruct
21.0 GB25.5 GB file
32K 31.0 GB · 128K —
IQ2_XS
Llama 4 Scout 17B 16E Instruct
35.9 GB31.8 GB file
32K 47.3 GB · 128K 83.8 GB
Qwen2.5 72B Instruct
22.8 GB27.1 GB file
32K 32.9 GB · 128K —
IQ2_S
Llama 4 Scout 17B 16E Instruct
37.4 GB32.3 GB file
32K 48.8 GB · 128K 85.3 GB
Qwen2.5 72B Instruct
23.7 GB27.9 GB file
32K 33.8 GB · 128K —
IQ2_M
Llama 4 Scout 17B 16E Instruct
40.3 GB39.1 GB file
32K 51.8 GB · 128K 88.3 GB
Qwen2.5 72B Instruct
25.5 GB29.3 GB file
32K 35.6 GB · 128K —
IQ3_XXS
Llama 4 Scout 17B 16E Instruct
46.3 GB45.7 GB file
32K 57.7 GB · 128K 94.3 GB
Qwen2.5 72B Instruct
29.1 GB31.8 GB file
32K 39.2 GB · 128K —
Q2_K_S
Llama 4 Scout 17B 16E Instruct
47.8 GB37.0 GB file
32K 59.2 GB · 128K 95.8 GB
Qwen2.5 72B Instruct
30.1 GB29.6 GB file
32K 40.1 GB · 128K —
IQ3_XS
Llama 4 Scout 17B 16E Instruct
49.3 GB44.3 GB file
32K 60.7 GB · 128K 97.3 GB
Qwen2.5 72B Instruct
31.0 GB32.8 GB file
32K 41.0 GB · 128K —
IQ3_S
Llama 4 Scout 17B 16E Instruct
50.8 GB46.8 GB file
32K 62.2 GB · 128K 98.7 GB
Qwen2.5 72B Instruct
31.9 GB34.5 GB file
32K 41.9 GB · 128K —
IQ3_M
Llama 4 Scout 17B 16E Instruct
53.8 GB47.5 GB file
32K 65.2 GB · 128K 102 GB
Qwen2.5 72B Instruct
33.7 GB35.5 GB file
32K 43.8 GB · 128K —
Q3_K_L
Llama 4 Scout 17B 16E Instruct
61.3 GB57.8 GB file
32K 72.7 GB · 128K 109 GB
Qwen2.5 72B Instruct
38.2 GB39.5 GB file
32K 48.3 GB · 128K —
IQ4_XS
Llama 4 Scout 17B 16E Instruct
64.2 GB57.7 GB file
32K 75.7 GB · 128K 112 GB
Qwen2.5 72B Instruct
40.1 GB39.7 GB file
32K 50.1 GB · 128K —
IQ4_NL
Llama 4 Scout 17B 16E Instruct
67.2 GB60.9 GB file
32K 78.6 GB · 128K 115 GB
Qwen2.5 72B Instruct
41.9 GB41.3 GB file
32K 51.9 GB · 128K —
Q4_1
Llama 4 Scout 17B 16E Instruct
67.2 GB67.6 GB file
32K 78.6 GB · 128K 115 GB
Qwen2.5 72B Instruct
41.9 GB45.7 GB file
32K 51.9 GB · 128K —
Q4_K_S
Llama 4 Scout 17B 16E Instruct
67.2 GB61.5 GB file
32K 78.6 GB · 128K 115 GB
Qwen2.5 72B Instruct
41.9 GB43.9 GB file
32K 51.9 GB · 128K —
Q5_0
Llama 4 Scout 17B 16E Instruct
not listed
Qwen2.5 72B Instruct
46.4 GB50.3 GB file
32K 56.5 GB · 128K —
Q5_K_S
Llama 4 Scout 17B 16E Instruct
82.2 GB74.3 GB file
32K 93.6 GB · 128K 130 GB
Qwen2.5 72B Instruct
51.0 GB51.4 GB file
32K 61.0 GB · 128K —
BF16
Llama 4 Scout 17B 16E Instruct
239 GB215.6 GB file
32K 250 GB · 128K 287 GB
Qwen2.5 72B Instruct
146 GB~145.4 GB file
32K 156 GB · 128K —
Llama 4 Scout 17B 16E Instruct
Ollama · Q4_K_M
ollama run hf.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF:Q4_K_MQwen2.5 72B Instruct
Ollama · Q4_K_M
ollama run hf.co/bartowski/Qwen2.5-72B-Instruct-GGUF:Q4_K_M| Spec | Llama 4 Scout 17B 16E Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| Publisher | Meta | Alibaba |
| Parameters | 108.6B | 72.7B |
| Active parameters | 17B per token | — |
| Architecture | — | Qwen2ForCausalLM |
| Context | — | 32K tokens |
| Modalities | Vision | Chat, Function-calling |
| License | Other | Other |
| Released | Apr 2025 | Sep 2024 |
Frequently Asked Questions
Which is better, Llama 4 Scout 17B 16E Instruct or Qwen2.5 72B Instruct?
Llama 4 Scout 17B 16E Instruct and Qwen2.5 72B Instruct match in llmrun Score, with values of 81.8 versus 81.7; neither fits 24 GB. Choose Llama 4 Scout 17B 16E Instruct for also does vision and newer release; choose Qwen2.5 72B Instruct for fits a 48 GB GPU and lighter on memory.
Which needs less VRAM, Llama 4 Scout 17B 16E Instruct or Qwen2.5 72B Instruct?
At Q4_K_M, Llama 4 Scout 17B 16E Instruct requires 71.7 GB while Qwen2.5 72B Instruct needs 44.6 GB, making Qwen2.5 72B Instruct the easier model to run on your local setup.
Can I run Llama 4 Scout 17B 16E Instruct or Qwen2.5 72B Instruct on a 16 GB GPU?
Llama 4 Scout 17B 16E Instruct does not fit (smallest quant needs 38.2 GB); Qwen2.5 72B Instruct does not fit (smallest quant needs 25.7 GB).