Mistral Medium 3.5 128B vs Mixtral 8x22B Instruct v0.1
Mistral Medium 3.5 128B leads llmrun Score 102.1 to 72.2; neither fits 24 GB.
Run Mistral Medium 3.5 128B in the cloud →
Model A · Mistral AI
Mistral Medium 3.5 128B127.7B · 256K context · Other · Mar 2026
Model B · Mistral AI
Mixtral 8x22B Instruct v0.1140.6B · 39.2B active · 64K context · Apache 2.0 · Apr 2024
Choose Mistral Medium 3.5 128B if you want…
Higher llmrun Score
102.1 vs 72.2
Stronger at reasoning
101.5 vs 78.5
Fits a Mac 64 GB
IQ3_S · 60.5 GB; Mixtral 8x22B Instruct v0.1 needs 42.7 GB at its smallest quant
Longer context window
256K vs 64K tokens
Newer release
Mar 2026 vs Apr 2024
Choose Mixtral 8x22B Instruct v0.1 if you want…
More permissive license
Apache 2.0 vs Other
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
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
12 GB
RTX 3060 12GB · 12 GB tier
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
24 GBreference
RTX 4090 · 24 GB tier
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
32 GB
RTX 5090 · 32 GB tier
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
48 GB
RTX A6000 · 48 GB tier
Mistral Medium 3.5 128B
IQ2_S · ~12 tok/s
46.1 GB · up to 16K
Mixtral 8x22B Instruct v0.1
IQ2_XS · ~37 tok/s
46.3 GB · up to 16K
Mac 32 GB
Mac Mini M4 · Macs
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
Mixtral 8x22B Instruct v0.1
Doesn't fit
smallest quant needs 42.7 GB
Mac 64 GB
Mac Studio M4 Max · Macs
Mistral Medium 3.5 128B
IQ3_S · ~7 tok/s
60.5 GB · up to 16Kbetter quant
Mixtral 8x22B Instruct v0.1
IQ2_M · ~22 tok/s
51.5 GB · up to 32K
Mac 128 GB
Mac Studio M4 Max · Macs
Mistral Medium 3.5 128B
Q4_K_M · ~5 tok/s
82.8 GB · up to 128K
Mixtral 8x22B Instruct v0.1
Q4_K_M · ~14 tok/s
88.4 GB · up to 64Kfaster
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Mistral Medium 3.5 128B
Mixtral 8x22B Instruct v0.1
Coding
Mistral Medium 3.5 128B
Mixtral 8x22B Instruct v0.1
no data
Science
Mistral Medium 3.5 128B
Mixtral 8x22B Instruct v0.1
no data
Reasoning
Mistral Medium 3.5 128B
Mixtral 8x22B Instruct v0.1
Mistral Medium 3.5 128B · #53 of 106 open models · #20 of 62 that fit ≤96 GB
Mixtral 8x22B Instruct v0.1 · #98 of 106 open models · #55 of 62 that fit ≤96 GB
Benchmarks
2 shared boards: Mistral Medium 3.5 128B leads 2, Mixtral 8x22B Instruct v0.1 leads 0 · Benchmarks imported Nov 2026
13 more boards (other shared and single-model boards)
Mistral Medium 3.5 128B
1426.4#28/188 open
ArenaLMArena · Oct 2026
Mixtral 8x22B Instruct v0.1
1229.7#136/188 open
ArenaLMArena · Oct 2026
Only Mistral Medium 3.5 128B (8)
- LMArena WebDev1264.0
- SciCode40.2%
- FrontierCode8.0%
- CritPt0.0%
- LMCA26.1%
- ALE-Bench764.0
- Surface Evolver Bench26.9%
- ProofBench9.0%
Only Mixtral 8x22B Instruct v0.1 (4)
- GPQA Diamond34.1%
- MMLU-Pro56.3%
- MATH Level 524.2%
- ForecastBench58.8
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
Mistral Medium 3.5 128B
55.3 GB46.6 GB file
32K 66.4 GB · 128K 102 GB
Mixtral 8x22B Instruct v0.1
60.5 GB52.1 GB file
32K 67.6 GB · 128K —
Q3_K_S
Mistral Medium 3.5 128B
56.9 GB54.4 GB file
32K 68.0 GB · 128K 103 GB
Mixtral 8x22B Instruct v0.1
62.3 GB61.5 GB file
32K 69.4 GB · 128K —
Q3_K_M
Mistral Medium 3.5 128B
63.3 GB60.6 GB file
32K 74.4 GB · 128K 110 GB
Mixtral 8x22B Instruct v0.1
69.3 GB67.8 GB file
32K 76.4 GB · 128K —
Q4_0
Mistral Medium 3.5 128B
64.9 GB71.0 GB file
32K 76.0 GB · 128K 111 GB
Mixtral 8x22B Instruct v0.1
not listed
Q4_K_M
Mistral Medium 3.5 128B
77.7 GB74.9 GB file
32K 88.7 GB · 128K 124 GB
Mixtral 8x22B Instruct v0.1
85.2 GB85.6 GB file
32K 92.2 GB · 128K —
Q5_K_M
Mistral Medium 3.5 128B
92.0 GB88.3 GB file
32K 103 GB · 128K 139 GB
Mixtral 8x22B Instruct v0.1
101 GB100.0 GB file
32K 108 GB · 128K —
Q6_K
Mistral Medium 3.5 128B
106 GB102.6 GB file
32K 117 GB · 128K 153 GB
Mixtral 8x22B Instruct v0.1
117 GB~116.0 GB file
32K 124 GB · 128K —
Q8_0
Mistral Medium 3.5 128B
129 GB132.9 GB file
32K 140 GB · 128K 175 GB
Mixtral 8x22B Instruct v0.1
141 GB149.4 GB file
32K 148 GB · 128K —
18 more quants
IQ2_XXS
Mistral Medium 3.5 128B
36.2 GB34.9 GB file
32K 47.2 GB · 128K 82.7 GB
Mixtral 8x22B Instruct v0.1
39.4 GB37.9 GB file
32K 46.5 GB · 128K —
IQ2_XS
Mistral Medium 3.5 128B
39.4 GB43.4 GB file
32K 50.4 GB · 128K 85.9 GB
Mixtral 8x22B Instruct v0.1
43.0 GB42.0 GB file
32K 50.0 GB · 128K —
IQ2_S
Mistral Medium 3.5 128B
41.0 GB46.1 GB file
32K 52.0 GB · 128K 87.5 GB
Mixtral 8x22B Instruct v0.1
44.7 GB42.6 GB file
32K 51.8 GB · 128K —
IQ2_M
Mistral Medium 3.5 128B
44.1 GB44.1 GB file
32K 55.2 GB · 128K 90.7 GB
Mixtral 8x22B Instruct v0.1
48.2 GB46.7 GB file
32K 55.3 GB · 128K —
IQ3_XXS
Mistral Medium 3.5 128B
50.5 GB49.3 GB file
32K 61.6 GB · 128K 97.0 GB
Mixtral 8x22B Instruct v0.1
not listed
Q2_K_S
Mistral Medium 3.5 128B
52.1 GB43.0 GB file
32K 63.2 GB · 128K 98.6 GB
Mixtral 8x22B Instruct v0.1
not listed
IQ3_XS
Mistral Medium 3.5 128B
53.7 GB54.9 GB file
32K 64.8 GB · 128K 100 GB
Mixtral 8x22B Instruct v0.1
58.8 GB58.2 GB file
32K 65.8 GB · 128K —
IQ3_S
Mistral Medium 3.5 128B
55.3 GB54.5 GB file
32K 66.4 GB · 128K 102 GB
Mixtral 8x22B Instruct v0.1
not listed
IQ3_M
Mistral Medium 3.5 128B
58.5 GB59.5 GB file
32K 69.6 GB · 128K 105 GB
Mixtral 8x22B Instruct v0.1
not listed
Q3_K_L
Mistral Medium 3.5 128B
66.5 GB67.0 GB file
32K 77.6 GB · 128K 113 GB
Mixtral 8x22B Instruct v0.1
72.8 GB72.6 GB file
32K 79.9 GB · 128K —
IQ4_XS
Mistral Medium 3.5 128B
69.7 GB67.1 GB file
32K 80.8 GB · 128K 116 GB
Mixtral 8x22B Instruct v0.1
76.4 GB76.4 GB file
32K 83.4 GB · 128K —
IQ4_NL
Mistral Medium 3.5 128B
72.9 GB70.9 GB file
32K 83.9 GB · 128K 119 GB
Mixtral 8x22B Instruct v0.1
not listed
Q4_1
Mistral Medium 3.5 128B
72.9 GB78.5 GB file
32K 83.9 GB · 128K 119 GB
Mixtral 8x22B Instruct v0.1
not listed
Q4_K_S
Mistral Medium 3.5 128B
72.9 GB71.2 GB file
32K 83.9 GB · 128K 119 GB
Mixtral 8x22B Instruct v0.1
79.9 GB80.5 GB file
32K 86.9 GB · 128K —
Q4_K_L
Mistral Medium 3.5 128B
79.3 GB79.6 GB file
32K 90.3 GB · 128K 126 GB
Mixtral 8x22B Instruct v0.1
not listed
Q5_K_S
Mistral Medium 3.5 128B
88.8 GB86.2 GB file
32K 99.9 GB · 128K 135 GB
Mixtral 8x22B Instruct v0.1
97.5 GB97.0 GB file
32K 105 GB · 128K —
Q5_K_L
Mistral Medium 3.5 128B
93.6 GB92.1 GB file
32K 105 GB · 128K 140 GB
Mixtral 8x22B Instruct v0.1
not listed
BF16
Mistral Medium 3.5 128B
256 GB250.1 GB file
32K 268 GB · 128K 303 GB
Mixtral 8x22B Instruct v0.1
282 GB~281.3 GB file
32K 289 GB · 128K —
Mistral Medium 3.5 128B
Ollama · Q4_K_M
ollama run hf.co/unsloth/Mistral-Medium-3.5-128B-GGUF:Q4_K_MMixtral 8x22B Instruct v0.1
Ollama · Q4_K_M
ollama run hf.co/MaziyarPanahi/Mixtral-8x22B-Instruct-v0.1-GGUF:Q4_K_M| Spec | Mistral Medium 3.5 128B | Mixtral 8x22B Instruct v0.1 |
|---|---|---|
| Publisher | Mistral AI | Mistral AI |
| Parameters | 127.7B | 140.6B |
| Active parameters | — | 39B per token |
| Architecture | Mistral3ForConditionalGeneration | MixtralForCausalLM |
| Context | 256K tokens | 64K tokens |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | Other | Apache 2.0 |
| Released | Mar 2026 | Apr 2024 |
Frequently Asked Questions
Which is better, Mistral Medium 3.5 128B or Mixtral 8x22B Instruct v0.1?
Mistral Medium 3.5 128B leads llmrun Score 102.1 to 72.2; neither fits 24 GB. Choose Mistral Medium 3.5 128B for higher llmrun Score and stronger at reasoning; choose Mixtral 8x22B Instruct v0.1 for more permissive license.
Which needs less VRAM, Mistral Medium 3.5 128B or Mixtral 8x22B Instruct v0.1?
At Q4_K_M, Mistral Medium 3.5 128B requires 77.7 GB while Mixtral 8x22B Instruct v0.1 needs 85.2 GB, making Mistral Medium 3.5 128B the easier model to run on your local setup.
Can I run Mistral Medium 3.5 128B or Mixtral 8x22B Instruct v0.1 on a 16 GB GPU?
Mistral Medium 3.5 128B does not fit (smallest quant needs 41.3 GB); Mixtral 8x22B Instruct v0.1 does not fit (smallest quant needs 42.7 GB).
Which has a longer context window, Mistral Medium 3.5 128B or Mixtral 8x22B Instruct v0.1?
Mistral Medium 3.5 128B supports 262,144 tokens and Mixtral 8x22B Instruct v0.1 supports 65,536 tokens.