RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run Ornith 1.5 35B A3B locally?

Ornith 1.5 35B A3B by ornith-ai has 36B parameters (3.0B active per token, 256 experts, 8 used per token). At 4-bit with an 8K context it needs about 21.4 GB of GPU memory. It fits on 48 of 65 GPUs and Macs we track. See all models that fit in 24 GB of VRAM.

21.4 GBQ4_K_M · 8K context
RTX 5090smallest consumer GPU that fits
M3 Pro 36GBsmallest Mac that fits
256Kmax 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 bartowski/Ornith-1.5-35B-A3B-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K) •rough13.1 GB13.2 GB13.7 GB15.6 GB
3-bit (Q3_K_M) •usable16.5 GB16.6 GB17.0 GB18.9 GB
4-bit (Q4_K_M) •good, most popular21.3 GB21.4 GB21.9 GB23.7 GB
5-bit (Q5_K_M) •very good24.7 GB24.8 GB25.2 GB27.1 GB
6-bit (Q6_K) •near lossless29.4 GB29.5 GB29.9 GB31.8 GB
8-bit (Q8_0) •effectively lossless36.2 GB36.2 GB36.7 GB38.6 GB
16-bit (F16/BF16) •original weights67.1 GB67.2 GB67.7 GB69.6 GB

Which GPUs and Macs run Ornith 1.5 35B A3B?

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 GBFitsQ2_K13.2 GB264details
RTX 309024 GBFitsQ3_K_M16.6 GB672details
RTX 409024 GBFitsQ3_K_M16.6 GB723details
RTX 509032 GBFitsQ5_K_M24.8 GB842details
RTX 5070 Ti16 GBFitsQ2_K13.2 GB821details
RX 7900 XTX24 GBFitsQ3_K_M16.6 GB689details
Mac M4 Pro 48GB48 GBFitsQ5_K_M24.8 GB128details
Mac M4 Max 128GB128 GBFitsF1667.2 GB92details
Mac M3 Ultra 512GB512 GBFitsF1667.2 GB138details
DGX Spark128 GBFitsF1667.2 GB46details
RTX 407012 GBNo———details
RTX 5060 Ti 16GB16 GBFitsQ2_K13.2 GB410details
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 GBFitsQ3_K_M16.6 GB723details
RTX 4060 Ti 8GB8 GBNo———details
RTX 4070 Super12 GBNo———details
RTX 4070 Ti12 GBNo———details
RTX 4070 Ti Super16 GBFitsQ2_K13.2 GB615details
RTX 408016 GBFitsQ2_K13.2 GB657details
RTX 4080 Super16 GBFitsQ2_K13.2 GB674details
RTX 50608 GBNo———details
RTX 507012 GBNo———details
RTX 508016 GBFitsQ2_K13.2 GB879details
2x RTX 30902×24 GBFitsQ8_036.2 GB297details
2x RTX 40902×24 GBFitsQ8_036.2 GB319details
2x RTX 50902×32 GBFitsQ8_036.2 GB568details
RTX A600048 GBFitsQ8_036.2 GB243details
RTX 6000 Ada48 GBFitsQ8_036.2 GB304details
RTX PRO 6000 Blackwell96 GBFitsF1667.2 GB302details
L40S48 GBFitsQ8_036.2 GB274details
A100 40GB40 GBFitsQ6_K29.5 GB610details
A100 80GB80 GBFitsF1667.2 GB344details
H100 PCIe80 GBFitsF1667.2 GB337details
H100 SXM80 GBFitsF1667.2 GB565details
H200141 GBFitsF1667.2 GB809details
RX 76008 GBNo———details
RX 7700 XT12 GBNo———details
RX 7800 XT16 GBFitsQ2_K13.2 GB571details
RX 7900 GRE16 GBFitsQ2_K13.2 GB528details
RX 7900 XT20 GBFitsQ3_K_M16.6 GB574details
RX 907016 GBFitsQ2_K13.2 GB586details
RX 9070 XT16 GBFitsQ2_K13.2 GB586details
Ryzen AI Max+ 395 128GB128 GBFitsF1667.2 GB43details
Arc A770 16GB16 GBFitsQ2_K13.2 GB513details
Mac M1 16GB16 GBNo———details
Mac M2 24GB24 GBFitsQ2_K13.2 GB92details
Mac M3 24GB24 GBFitsQ2_K13.2 GB92details
Mac M4 16GB16 GBNo———details
Mac M4 32GB32 GBFitsQ3_K_M16.6 GB86details
Mac M1 Pro 32GB32 GBFitsQ3_K_M16.6 GB144details
Mac M3 Pro 36GB36 GBFitsQ4_K_M21.4 GB82details
Mac M4 Pro 24GB24 GBFitsQ2_K13.2 GB250details
Mac M4 Pro 64GB64 GBFitsQ8_036.2 GB87details
Mac M1 Max 64GB64 GBFitsQ8_036.2 GB127details
Mac M2 Max 96GB96 GBFitsQ8_036.2 GB127details
Mac M3 Max 128GB128 GBFitsF1667.2 GB67details
Mac M4 Max 64GB64 GBFitsQ8_036.2 GB173details
Mac M2 Ultra 192GB192 GBFitsF1667.2 GB135details
Mac M3 Ultra 256GB256 GBFitsF1667.2 GB138details

Questions

How much VRAM does Ornith 1.5 35B A3B need?

About 21.4 GB at 4-bit (Q4_K_M) with an 8K context: 20.4 GB of weights (real GGUF file size), 0.2 GB of KV cache and 0.9 GB of runtime overhead. At 8-bit it needs about 36.2 GB.

What is the smallest GPU that runs Ornith 1.5 35B A3B?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 5090 (32 GB).

Can I run Ornith 1.5 35B A3B on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M3 Pro 36GB 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.

Ornith 1.5 9B

9.7B · 6.6 GB at 4-bit

Ornith 1.5 122B

125B · 72.3 GB at 4-bit

Qwen3.6 35B A3B

36B · 22.1 GB at 4-bit

Qwen3.5 35B A3B

36B · 21.5 GB at 4-bit

Hermes 4.3 36B

36B · 23.0 GB at 4-bit

Seed OSS 36B Instruct

36B · 23.0 GB at 4-bit

Model facts

Hugging Face repoornith-ai/Ornith-1.5-35B-A3B
Parameters35,951,822,704 (36B) · ~3.0B active (from the model name)
Layers / hidden size40 / 2048
AttentionGQA (hybrid: 30 linear/state layers); 16 heads, 2 KV heads, head dim 256
KV cache per token (FP16)20.0 KiB
Max context262,144 tokens
Licensemit
Released on HFAug 18, 2026
Downloads (30d) / likes325,171 / 800

Sources: Hugging Face model API · config.json (ornith-ai/Ornith-1.5-35B-A3B) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.