Gemma 2 27B IT vs Mixtral 8x7B Instruct v0.1
Gemma 2 27B IT leads llmrun Score 72.7 to 65.1 (ranges overlap); both fit 24 GB (Gemma 2 27B IT at Q4_K_M, Mixtral 8x7B Instruct v0.1 at IQ3_M); Mixtral 8x7B Instruct v0.1 is 2.5× faster on RTX 4090 (~92 vs ~37 tok/s).
Model B · Mistral AI
Mixtral 8x7B Instruct v0.146.7B · 12.9B active · 32K context · Apache 2.0 · Dec 2023
Choose Gemma 2 27B IT if you want…
Higher llmrun Score
72.7 vs 65.1, ranges overlap
Ahead on the benchmarks
3 of 3 shared boards
Fits a 16 GB GPU
IQ3_M · 15 GB; Mixtral 8x7B Instruct v0.1 needs 15.3 GB at its smallest quant
Lighter on memory
18.0 vs 28.6 GB at Q4_K_M
Newer release
Jun 2024 vs Dec 2023
Choose Mixtral 8x7B Instruct v0.1 if you want…
2.5× faster on RTX 4090
~92 vs ~37 tok/s
Longer context window
32K vs 8K tokens
More permissive license
Apache 2.0 vs Gemma Terms
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
Gemma 2 27B IT
Doesn't fit
smallest quant needs 9.8 GB
Mixtral 8x7B Instruct v0.1
Doesn't fit
smallest quant needs 15.3 GB
12 GB
RTX 3060 12GB · 12 GB tier
Gemma 2 27B IT
IQ2_M · ~23 tok/s
11.7 GB · up to 8Kfits
Mixtral 8x7B Instruct v0.1
Doesn't fit
smallest quant needs 15.3 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Gemma 2 27B IT
IQ3_M · ~22 tok/s
15 GB · up to 8Kbetter quant
Mixtral 8x7B Instruct v0.1
IQ2_XXS · ~69 tok/s
15.3 GB · up to 16K
24 GBreference
RTX 4090 · 24 GB tier
Gemma 2 27B IT
Q4_K_M · ~37 tok/s
19.5 GB · up to 8Kmore headroom
Mixtral 8x7B Instruct v0.1
IQ3_M · ~92 tok/s
23.5 GB · up to 16K
32 GB
RTX 5090 · 32 GB tier
Gemma 2 27B IT
Q4_K_M · ~65 tok/s
19.5 GB · up to 8K
Mixtral 8x7B Instruct v0.1
Q4_K_M · ~117 tok/s
30.5 GB · up to 16Kfaster
48 GB
RTX A6000 · 48 GB tier
Gemma 2 27B IT
Q4_K_M · ~28 tok/s
19.5 GB · up to 8K
Mixtral 8x7B Instruct v0.1
Q4_K_M · ~57 tok/s
30.5 GB · up to 32Kfaster
Mac 32 GB
Mac Mini M4 · Macs
Gemma 2 27B IT
Q4_K_M · ~5 tok/s
19.5 GB · up to 8Kmore headroom
Mixtral 8x7B Instruct v0.1
IQ4_XS · ~11 tok/s
27.6 GB · up to 16K
Mac 64 GB
Mac Studio M4 Max · Macs
Gemma 2 27B IT
Q4_K_M · ~21 tok/s
19.5 GB · up to 8K
Mixtral 8x7B Instruct v0.1
Q4_K_M · ~37 tok/s
30.5 GB · up to 32Kfaster
Mac 128 GB
Mac Studio M4 Max · Macs
Gemma 2 27B IT
Q4_K_M · ~21 tok/s
19.5 GB · up to 8K
Mixtral 8x7B Instruct v0.1
Q4_K_M · ~37 tok/s
30.5 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
Gemma 2 27B IT
Mixtral 8x7B Instruct v0.1
Reasoning
Gemma 2 27B IT
no data
Mixtral 8x7B Instruct v0.1
Gemma 2 27B IT · #91 of 100 open models · #28 of 35 that fit 24 GB
Mixtral 8x7B Instruct v0.1 · #96 of 100 open models · #31 of 35 that fit 24 GB
Benchmarks
3 shared boards: Gemma 2 27B IT leads 3, Mixtral 8x7B Instruct v0.1 leads 0 · Benchmarks imported Oct 2026
Gemma 2 27B IT
36.5%#74/98 open
IndependentEpoch AI · Jun 2024
Mixtral 8x7B Instruct v0.1
30.6%#81/98 open
IndependentEpoch AI · Dec 2023
Gemma 2 27B IT
56.5%#62/145 open
IndependentTIGER-Lab
Mixtral 8x7B Instruct v0.1
43.3%#93/145 open
IndependentTIGER-Lab
Gemma 2 27B IT
27.9%#24/39 open
IndependentEpoch AI · Jun 2024
Mixtral 8x7B Instruct v0.1
10.0%#34/39 open
IndependentEpoch AI · Dec 2023
5 more boards (other shared and single-model boards)
Gemma 2 27B IT
1289.5#112/187 open
ArenaLMArena · Oct 2026
Mixtral 8x7B Instruct v0.1
1197.3#147/187 open
ArenaLMArena · Oct 2026
Only Gemma 2 27B IT (2)
- AIME 2024/20251.4%
- MMLU75.7%
Only Mixtral 8x7B Instruct v0.1 (2)
- DTBench49.6%
- ForecastBench56.3
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
Gemma 2 27B IT
12.7 GB10.4 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
20.4 GB15.6 GB file
32K 24.5 GB · 128K —
Q3_K_S
Gemma 2 27B IT
13.1 GB12.2 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
21.0 GB20.4 GB file
32K 25.0 GB · 128K —
Q3_K_M
Gemma 2 27B IT
14.6 GB13.4 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
23.3 GB20.4 GB file
32K 27.4 GB · 128K —
Q4_0
Gemma 2 27B IT
15.0 GB15.7 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
23.9 GB26.4 GB file
32K 28.0 GB · 128K —
Q4_K_M
Gemma 2 27B IT
18.0 GB16.6 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
28.6 GB26.4 GB file
32K 32.6 GB · 128K —
Q5_K_M
Gemma 2 27B IT
21.3 GB19.4 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
33.8 GB32.2 GB file
32K 37.9 GB · 128K —
Q6_K
Gemma 2 27B IT
24.7 GB22.3 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
39.1 GB38.4 GB file
32K 43.1 GB · 128K —
Q8_0
Gemma 2 27B IT
30.0 GB28.9 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
47.3 GB49.6 GB file
32K 51.3 GB · 128K —
19 more quants
IQ2_XXS
Gemma 2 27B IT
8.2 GB7.6 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
13.4 GB12.6 GB file
32K 17.4 GB · 128K —
IQ2_XS
Gemma 2 27B IT
9.0 GB8.4 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
14.6 GB13.9 GB file
32K 18.6 GB · 128K —
IQ2_S
Gemma 2 27B IT
9.4 GB8.7 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
15.2 GB14.1 GB file
32K 19.2 GB · 128K —
IQ2_M
Gemma 2 27B IT
10.1 GB9.4 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
16.3 GB15.5 GB file
32K 20.4 GB · 128K —
IQ3_XXS
Gemma 2 27B IT
11.6 GB10.8 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
18.7 GB18.2 GB file
32K 22.7 GB · 128K —
Q2_K_S
Gemma 2 27B IT
not listed
Mixtral 8x7B Instruct v0.1
19.3 GB16.0 GB file
32K 23.3 GB · 128K —
IQ3_XS
Gemma 2 27B IT
12.4 GB11.6 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
19.8 GB19.4 GB file
32K 23.9 GB · 128K —
IQ3_S
Gemma 2 27B IT
12.7 GB12.2 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
20.4 GB20.4 GB file
32K 24.5 GB · 128K —
IQ3_M
Gemma 2 27B IT
13.5 GB12.5 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
21.6 GB21.4 GB file
32K 25.6 GB · 128K —
Q3_K_L
Gemma 2 27B IT
15.4 GB14.5 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
24.5 GB24.2 GB file
32K 28.5 GB · 128K —
IQ4_XS
Gemma 2 27B IT
16.1 GB14.8 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
25.7 GB25.1 GB file
32K 29.7 GB · 128K —
Q4_1
Gemma 2 27B IT
not listed
Mixtral 8x7B Instruct v0.1
26.8 GB29.3 GB file
32K 30.9 GB · 128K —
Q4_K_S
Gemma 2 27B IT
16.9 GB15.7 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
26.8 GB26.7 GB file
32K 30.9 GB · 128K —
Q4_K_L
Gemma 2 27B IT
18.3 GB16.9 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
not listed
Q5_0
Gemma 2 27B IT
18.7 GB18.9 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
29.8 GB32.2 GB file
32K 33.8 GB · 128K —
Q5_1
Gemma 2 27B IT
not listed
Mixtral 8x7B Instruct v0.1
32.7 GB35.1 GB file
32K 36.7 GB · 128K —
Q5_K_S
Gemma 2 27B IT
20.6 GB18.9 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
32.7 GB32.2 GB file
32K 36.7 GB · 128K —
Q5_K_L
Gemma 2 27B IT
21.7 GB19.7 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
not listed
BF16
Gemma 2 27B IT
59.9 GB~54.5 GB file
32K — · 128K —
Mixtral 8x7B Instruct v0.1
94.0 GB~93.4 GB file
32K 98.0 GB · 128K —
Gemma 2 27B IT
Ollama · Q4_K_M
ollama run hf.co/bartowski/gemma-2-27b-it-GGUF:Q4_K_MMixtral 8x7B Instruct v0.1
Ollama · Q4_K_M
ollama run hf.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M| Spec | Gemma 2 27B IT | Mixtral 8x7B Instruct v0.1 |
|---|---|---|
| Publisher | Mistral AI | |
| Parameters | 27.2B | 46.7B |
| Active parameters | — | 13B per token |
| Architecture | — | MixtralForCausalLM |
| Context | 8K tokens | 32K tokens |
| Modalities | Chat | Chat |
| License | Gemma Terms | Apache 2.0 |
| Released | Jun 2024 | Dec 2023 |
Frequently Asked Questions
Which is better, Gemma 2 27B IT or Mixtral 8x7B Instruct v0.1?
Gemma 2 27B IT leads llmrun Score 72.7 to 65.1 (ranges overlap); both fit 24 GB (Gemma 2 27B IT at Q4_K_M, Mixtral 8x7B Instruct v0.1 at IQ3_M); Mixtral 8x7B Instruct v0.1 is 2.5× faster on RTX 4090 (~92 vs ~37 tok/s). Choose Gemma 2 27B IT for higher llmrun Score and ahead on the benchmarks; choose Mixtral 8x7B Instruct v0.1 for 2.5× faster on RTX 4090 and longer context window.
Which needs less VRAM, Gemma 2 27B IT or Mixtral 8x7B Instruct v0.1?
At Q4_K_M, Gemma 2 27B IT requires 18.0 GB while Mixtral 8x7B Instruct v0.1 needs 28.6 GB, making Gemma 2 27B IT the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 37 tok/s for Gemma 2 27B IT (Q4_K_M) and 92 tok/s for Mixtral 8x7B Instruct v0.1 (IQ3_M), so Mixtral 8x7B Instruct v0.1 is faster. Estimates, ±20%.
Can I run Gemma 2 27B IT or Mixtral 8x7B Instruct v0.1 on a 16 GB GPU?
Gemma 2 27B IT fits at IQ3_M; Mixtral 8x7B Instruct v0.1 fits at IQ2_XXS.
Which has a longer context window, Gemma 2 27B IT or Mixtral 8x7B Instruct v0.1?
Gemma 2 27B IT supports 8,192 tokens and Mixtral 8x7B Instruct v0.1 supports 32,768 tokens.