RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run Nous Hermes 2 Mixtral 8x7B DPO locally?

Nous Hermes 2 Mixtral 8x7B DPO by NousResearch has 47B parameters (13B active per token, 8 experts, 2 used per token). At 4-bit with an 8K context it needs about 28.0 GB of GPU memory. It fits on 33 of 65 GPUs and Macs we track. See all models that fit in 32 GB of VRAM.

28.0 GBQ4_K_M · 8K context
nonesmallest consumer GPU that fits
M4 Pro 48GBsmallest Mac that fits
32Kmax context
GQAattention type

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from TheBloke/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx
2-bit (Q2_K) •rough17.1 GB17.6 GB20.6 GB
3-bit (Q3_K_M) •usable22.0 GB22.5 GB25.5 GB
4-bit (Q4_K_M) •good, most popular27.5 GB28.0 GB31.0 GB
5-bit (Q5_K_M) •very good31.9 GB32.4 GB35.4 GB
6-bit (Q6_K) •near lossless36.7 GB37.2 GB40.2 GB
8-bit (Q8_0) •effectively lossless47.2 GB47.7 GB50.7 GB
16-bit (F16/BF16)original weights88.0 GB88.5 GB91.5 GB

Which GPUs and Macs run Nous Hermes 2 Mixtral 8x7B DPO?

Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).

HardwareMemoryFits?Best quantNeedsMax tok/s (est.)
RTX 3060 12GB12 GBNo———details
RTX 4060 Ti 16GB16 GBNo———details
RTX 309024 GBFitsQ2_K17.6 GB196details
RTX 409024 GBFitsQ2_K17.6 GB211details
RTX 509032 GBFitsQ3_K_M22.5 GB288details
RTX 5070 Ti16 GBNo———details
RX 7900 XTX24 GBFitsQ2_K17.6 GB201details
Mac M4 Pro 48GB48 GBFitsQ4_K_M28.0 GB35details
Mac M4 Max 128GB128 GBFitsQ8_047.7 GB40details
Mac M3 Ultra 512GB512 GBFitsF1688.5 GB32details
DGX Spark128 GBFitsF1688.5 GB11details
RTX 407012 GBNo———details
RTX 5060 Ti 16GB16 GBNo———details
RTX 40608 GBNo———details
Arc B58012 GBNo———details
RTX 3060 Ti8 GBNo———details
RTX 30708 GBNo———details
RTX 3080 10GB10 GBNo———details
RTX 3080 12GB12 GBNo———details
RTX 3090 Ti24 GBFitsQ2_K17.6 GB211details
RTX 4060 Ti 8GB8 GBNo———details
RTX 4070 Super12 GBNo———details
RTX 4070 Ti12 GBNo———details
RTX 4070 Ti Super16 GBNo———details
RTX 408016 GBNo———details
RTX 4080 Super16 GBNo———details
RTX 50608 GBNo———details
RTX 507012 GBNo———details
RTX 508016 GBNo———details
2x RTX 30902×24 GBFitsQ6_K37.2 GB88details
2x RTX 40902×24 GBFitsQ6_K37.2 GB95details
2x RTX 50902×32 GBFitsQ8_047.7 GB131details
RTX A600048 GBFitsQ6_K37.2 GB73details
RTX 6000 Ada48 GBFitsQ6_K37.2 GB91details
RTX PRO 6000 Blackwell96 GBFitsQ8_047.7 GB131details
L40S48 GBFitsQ6_K37.2 GB82details
A100 40GB40 GBFitsQ5_K_M32.4 GB170details
A100 80GB80 GBFitsQ8_047.7 GB149details
H100 PCIe80 GBFitsQ8_047.7 GB146details
H100 SXM80 GBFitsQ8_047.7 GB245details
H200141 GBFitsF1688.5 GB186details
RX 76008 GBNo———details
RX 7700 XT12 GBNo———details
RX 7800 XT16 GBNo———details
RX 7900 GRE16 GBNo———details
RX 7900 XT20 GBTightQ2_K17.6 GB168details
RX 907016 GBNo———details
RX 9070 XT16 GBNo———details
Ryzen AI Max+ 395 128GB128 GBFitsF1688.5 GB9.9details
Arc A770 16GB16 GBNo———details
Mac M1 16GB16 GBNo———details
Mac M2 24GB24 GBNo———details
Mac M3 24GB24 GBNo———details
Mac M4 16GB16 GBNo———details
Mac M4 32GB32 GBFitsQ2_K17.6 GB25details
Mac M1 Pro 32GB32 GBFitsQ2_K17.6 GB42details
Mac M3 Pro 36GB36 GBFitsQ2_K17.6 GB31details
Mac M4 Pro 24GB24 GBNo———details
Mac M4 Pro 64GB64 GBFitsQ6_K37.2 GB26details
Mac M1 Max 64GB64 GBFitsQ6_K37.2 GB38details
Mac M2 Max 96GB96 GBFitsQ8_047.7 GB29details
Mac M3 Max 128GB128 GBFitsQ8_047.7 GB29details
Mac M4 Max 64GB64 GBFitsQ6_K37.2 GB52details
Mac M2 Ultra 192GB192 GBFitsF1688.5 GB31details
Mac M3 Ultra 256GB256 GBFitsF1688.5 GB32details

Questions

How much VRAM does Nous Hermes 2 Mixtral 8x7B DPO need?

About 28.0 GB at 4-bit (Q4_K_M) with an 8K context: 26.5 GB of weights (real GGUF file size), 1.0 GB of KV cache and 0.5 GB of runtime overhead. At 8-bit it needs about 47.7 GB.

What is the smallest GPU that runs Nous Hermes 2 Mixtral 8x7B DPO?

No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the A100 40GB (40 GB).

Can I run Nous Hermes 2 Mixtral 8x7B DPO on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M4 Pro 48GB or larger, using the default macOS GPU memory limit.

Similar models

Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.

Hermes 4.3 36B

36B · 23.0 GB at 4-bit

Nous Hermes 2 Yi 34B

34B · 22.1 GB at 4-bit

Arete 27B

27B · 17.4 GB at 4-bit

Kimi Linear 48B A3B Instruct

49B · 28.9 GB at 4-bit

falcon 40b

42B · 25.2 GB at 4-bit

flint

40B · 23.6 GB at 4-bit

Model facts

Hugging Face repoNousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
Parameters46,702,809,088 (47B) · ~13B active (computed from config)
Layers / hidden size32 / 4096
AttentionGQA; 32 heads, 8 KV heads, head dim 128
KV cache per token (FP16)128.0 KiB
Max context32,768 tokens
Licenseapache-2.0
Released on HFJan 11, 2024
Downloads (30d) / likes10,572 / 461

Sources: Hugging Face model API · config.json (NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.