Mixtral 8x22B Instruct v0.1 vs Qwen2 72B Instruct
Qwen2 72B Instruct leads llmrun Score 77.5 to 71.6 (ranges overlap); neither fits 24 GB.
Model A · Mistral AI
Mixtral 8x22B Instruct v0.1140.6B · 39.2B active · 64K context · Apache 2.0 · Apr 2024
Choose Mixtral 8x22B Instruct v0.1 if you want…
Longer context window
64K vs 32K tokens
Also does function-calling
Qwen2 72B Instruct doesn't list it
More permissive license
Apache 2.0 vs Other
Choose Qwen2 72B Instruct if you want…
Higher llmrun Score
77.5 vs 71.6, ranges overlap
Ahead on the benchmarks
4 of 4 shared boards
Fits a 48 GB GPU
Q4_K_M · 49.3 GB; Mixtral 8x22B Instruct v0.1 needs 42.7 GB at its smallest quant
Fits a Mac 64 GB
Q4_K_M · 49.3 GB; Mixtral 8x22B Instruct v0.1 needs 42.7 GB at its smallest quant
Lighter on memory
44.6 vs 85.2 GB at Q4_K_M
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
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
Qwen2 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
12 GB
RTX 3060 12GB · 12 GB tier
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
Qwen2 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
Qwen2 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
24 GBreference
RTX 4090 · 24 GB tier
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
Qwen2 72B Instruct
Doesn't fit
smallest quant needs 25.7 GB
32 GB
RTX 5090 · 32 GB tier
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
Qwen2 72B Instruct
IQ2_M · ~46 tok/s
30.2 GB · up to 16Kfits
48 GB
RTX A6000 · 48 GB tier
Mixtral 8x22B Instruct v0.1
IQ2_XS · ~37 tok/s
46.3 GB · up to 16Kmore headroom
Qwen2 72B Instruct
Q4_K_M · ~11 tok/stight
49.3 GB · up to 8K
Mac 32 GB
Mac Mini M4 · Macs
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
Qwen2 72B Instruct
IQ2_S · ~4 tok/s
28.4 GB · up to 16Kfits
Mac 64 GB
Mac Studio M4 Max · Macs
Mixtral 8x22B Instruct v0.1
IQ2_M · ~22 tok/s
51.5 GB · up to 32K
Qwen2 72B Instruct
Q4_K_M · ~9 tok/s
49.3 GB · up to 32Kmore headroom
Mac 128 GB
Mac Studio M4 Max · Macs
Mixtral 8x22B Instruct v0.1
Q4_K_M · ~14 tok/s
88.4 GB · up to 64Kfaster
Qwen2 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
Mixtral 8x22B Instruct v0.1
Qwen2 72B Instruct
Reasoning
Mixtral 8x22B Instruct v0.1
Qwen2 72B Instruct
no data
Mixtral 8x22B Instruct v0.1 · #92 of 100 open models · #53 of 60 that fit ≤96 GB
Qwen2 72B Instruct · #88 of 100 open models · #38 of 49 that fit ≤64 GB
Benchmarks
4 shared boards: Mixtral 8x22B Instruct v0.1 leads 0, Qwen2 72B Instruct leads 4 · Benchmarks imported Oct 2026
Mixtral 8x22B Instruct v0.1
34.1%#76/98 open
IndependentEpoch AI · Apr 2024
Qwen2 72B Instruct
40.8%#69/98 open
IndependentEpoch AI · Jun 2024
Mixtral 8x22B Instruct v0.1
56.3%#63/145 open
IndependentTIGER-Lab
Qwen2 72B Instruct
64.4%#49/145 open
IndependentTIGER-Lab
Mixtral 8x22B Instruct v0.1
24.2%#27/39 open
IndependentEpoch AI · Apr 2024
Qwen2 72B Instruct
39.1%#22/39 open
IndependentEpoch AI · Jun 2024
Mixtral 8x22B Instruct v0.1
3.2%#45/46 open
IndependentEpoch AI · Apr 2024
Qwen2 72B Instruct
11.3%#43/46 open
IndependentEpoch AI · Jun 2024
5 more boards (other shared and single-model boards)
Mixtral 8x22B Instruct v0.1
1229.7#135/187 open
ArenaLMArena · Oct 2026
Qwen2 72B Instruct
1261.9#126/187 open
ArenaLMArena · Oct 2026
Only Mixtral 8x22B Instruct v0.1 (2)
- DTBench55.1%
- ForecastBench56.3
Only Qwen2 72B Instruct (2)
- MMLU82.4%
- 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
Mixtral 8x22B Instruct v0.1
60.5 GB52.1 GB file
32K 67.6 GB · 128K —
Qwen2 72B Instruct
31.9 GB29.8 GB file
32K 41.9 GB · 128K —
Q3_K_S
Mixtral 8x22B Instruct v0.1
62.3 GB61.5 GB file
32K 69.4 GB · 128K —
Qwen2 72B Instruct
32.8 GB34.5 GB file
32K 42.9 GB · 128K —
Q3_K_M
Mixtral 8x22B Instruct v0.1
69.3 GB67.8 GB file
32K 76.4 GB · 128K —
Qwen2 72B Instruct
36.4 GB37.7 GB file
32K 46.5 GB · 128K —
Q4_0
Mixtral 8x22B Instruct v0.1
not listed
Qwen2 72B Instruct
37.3 GB41.4 GB file
32K 47.4 GB · 128K —
Q4_K_M
Mixtral 8x22B Instruct v0.1
85.2 GB85.6 GB file
32K 92.2 GB · 128K —
Qwen2 72B Instruct
44.6 GB47.4 GB file
32K 54.7 GB · 128K —
Q5_K_M
Mixtral 8x22B Instruct v0.1
101 GB100.0 GB file
32K 108 GB · 128K —
Qwen2 72B Instruct
52.8 GB54.4 GB file
32K 62.8 GB · 128K —
Q6_K
Mixtral 8x22B Instruct v0.1
117 GB~116.0 GB file
32K 124 GB · 128K —
Qwen2 72B Instruct
61.0 GB64.3 GB file
32K 71.0 GB · 128K —
Q8_0
Mixtral 8x22B Instruct v0.1
141 GB149.4 GB file
32K 148 GB · 128K —
Qwen2 72B Instruct
73.7 GB77.3 GB file
32K 83.8 GB · 128K —
14 more quants
IQ2_XXS
Mixtral 8x22B Instruct v0.1
39.4 GB37.9 GB file
32K 46.5 GB · 128K —
Qwen2 72B Instruct
21.0 GB25.5 GB file
32K 31.0 GB · 128K —
IQ2_XS
Mixtral 8x22B Instruct v0.1
43.0 GB42.0 GB file
32K 50.0 GB · 128K —
Qwen2 72B Instruct
22.8 GB27.1 GB file
32K 32.9 GB · 128K —
IQ2_S
Mixtral 8x22B Instruct v0.1
44.7 GB42.6 GB file
32K 51.8 GB · 128K —
Qwen2 72B Instruct
23.7 GB27.9 GB file
32K 33.8 GB · 128K —
IQ2_M
Mixtral 8x22B Instruct v0.1
48.2 GB46.7 GB file
32K 55.3 GB · 128K —
Qwen2 72B Instruct
25.5 GB29.3 GB file
32K 35.6 GB · 128K —
IQ3_XXS
Mixtral 8x22B Instruct v0.1
not listed
Qwen2 72B Instruct
29.1 GB31.8 GB file
32K 39.2 GB · 128K —
IQ3_XS
Mixtral 8x22B Instruct v0.1
58.8 GB58.2 GB file
32K 65.8 GB · 128K —
Qwen2 72B Instruct
31.0 GB32.8 GB file
32K 41.0 GB · 128K —
IQ3_S
Mixtral 8x22B Instruct v0.1
not listed
Qwen2 72B Instruct
31.9 GB34.5 GB file
32K 41.9 GB · 128K —
IQ3_M
Mixtral 8x22B Instruct v0.1
not listed
Qwen2 72B Instruct
33.7 GB35.5 GB file
32K 43.8 GB · 128K —
Q3_K_L
Mixtral 8x22B Instruct v0.1
72.8 GB72.6 GB file
32K 79.9 GB · 128K —
Qwen2 72B Instruct
38.2 GB39.5 GB file
32K 48.3 GB · 128K —
IQ4_XS
Mixtral 8x22B Instruct v0.1
76.4 GB76.4 GB file
32K 83.4 GB · 128K —
Qwen2 72B Instruct
40.1 GB39.7 GB file
32K 50.1 GB · 128K —
Q4_K_S
Mixtral 8x22B Instruct v0.1
79.9 GB80.5 GB file
32K 86.9 GB · 128K —
Qwen2 72B Instruct
41.9 GB43.9 GB file
32K 51.9 GB · 128K —
Q5_0
Mixtral 8x22B Instruct v0.1
not listed
Qwen2 72B Instruct
46.4 GB50.2 GB file
32K 56.5 GB · 128K —
Q5_K_S
Mixtral 8x22B Instruct v0.1
97.5 GB97.0 GB file
32K 105 GB · 128K —
Qwen2 72B Instruct
51.0 GB51.4 GB file
32K 61.0 GB · 128K —
BF16
Mixtral 8x22B Instruct v0.1
282 GB~281.3 GB file
32K 289 GB · 128K —
Qwen2 72B Instruct
146 GB~145.4 GB file
32K 156 GB · 128K —
Mixtral 8x22B Instruct v0.1
Ollama · Q4_K_M
ollama run hf.co/MaziyarPanahi/Mixtral-8x22B-Instruct-v0.1-GGUF:Q4_K_MQwen2 72B Instruct
Ollama · Q4_K_M
ollama run hf.co/mradermacher/Qwen2-72B-Instruct-i1-GGUF:Q4_K_M| Spec | Mixtral 8x22B Instruct v0.1 | Qwen2 72B Instruct |
|---|---|---|
| Publisher | Mistral AI | Alibaba |
| Parameters | 140.6B | 72.7B |
| Active parameters | 39B per token | — |
| Architecture | MixtralForCausalLM | Qwen2ForCausalLM |
| Context | 64K tokens | 32K tokens |
| Modalities | Chat, Function-calling | Chat |
| License | Apache 2.0 | Other |
| Released | Apr 2024 | May 2024 |
Frequently Asked Questions
Which is better, Mixtral 8x22B Instruct v0.1 or Qwen2 72B Instruct?
Qwen2 72B Instruct leads llmrun Score 77.5 to 71.6 (ranges overlap); neither fits 24 GB. Choose Mixtral 8x22B Instruct v0.1 for longer context window and also does function-calling; choose Qwen2 72B Instruct for higher llmrun Score and ahead on the benchmarks.
Which needs less VRAM, Mixtral 8x22B Instruct v0.1 or Qwen2 72B Instruct?
At Q4_K_M, Mixtral 8x22B Instruct v0.1 requires 85.2 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 Mixtral 8x22B Instruct v0.1 or Qwen2 72B Instruct on a 16 GB GPU?
Mixtral 8x22B Instruct v0.1 does not fit (smallest quant needs 42.7 GB); Qwen2 72B Instruct does not fit (smallest quant needs 25.7 GB).
Which has a longer context window, Mixtral 8x22B Instruct v0.1 or Qwen2 72B Instruct?
Mixtral 8x22B Instruct v0.1 supports 65,536 tokens and Qwen2 72B Instruct supports 32,768 tokens.