RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run Ornith 1.5 9B locally?

Ornith 1.5 9B by ornith-ai has 9.7B parameters. At 4-bit with an 8K context it needs about 6.6 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 8 GB of VRAM.

6.6 GBQ4_K_M · 8K context
RTX 4060smallest consumer GPU that fits
M1 16GBsmallest 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-1.5-9B-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K) •rough4.8 GB4.9 GB5.7 GB8.7 GB
3-bit (Q3_K_M) •usable5.6 GB5.7 GB6.5 GB9.5 GB
4-bit (Q4_K_M) •good, most popular6.5 GB6.6 GB7.4 GB10.4 GB
5-bit (Q5_K_M) •very good7.4 GB7.5 GB8.3 GB11.3 GB
6-bit (Q6_K) •near lossless8.2 GB8.3 GB9.0 GB12.0 GB
8-bit (Q8_0) •effectively lossless9.9 GB10.0 GB10.8 GB13.8 GB
16-bit (F16/BF16) •original weights17.7 GB17.8 GB18.6 GB21.6 GB

Which GPUs and Macs run Ornith 1.5 9B?

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 GBFitsQ8_010.0 GB38details
RTX 4060 Ti 16GB16 GBFitsQ8_010.0 GB30details
RTX 309024 GBFitsF1617.8 GB52details
RTX 409024 GBFitsF1617.8 GB56details
RTX 509032 GBFitsF1617.8 GB100details
RTX 5070 Ti16 GBFitsQ8_010.0 GB94details
RX 7900 XTX24 GBFitsF1617.8 GB54details
Mac M4 Pro 48GB48 GBFitsF1617.8 GB15details
Mac M4 Max 128GB128 GBFitsF1617.8 GB30details
Mac M3 Ultra 512GB512 GBFitsF1617.8 GB46details
DGX Spark128 GBFitsF1617.8 GB15details
RTX 407012 GBFitsQ8_010.0 GB53details
RTX 5060 Ti 16GB16 GBFitsQ8_010.0 GB47details
RTX 40608 GBFitsQ4_K_M6.6 GB46details
Arc B58012 GBFitsQ8_010.0 GB48details
RTX 3060 Ti8 GBFitsQ4_K_M6.6 GB76details
RTX 30708 GBFitsQ4_K_M6.6 GB76details
RTX 3080 10GB10 GBFitsQ6_K8.3 GB99details
RTX 3080 12GB12 GBFitsQ8_010.0 GB96details
RTX 3090 Ti24 GBFitsF1617.8 GB56details
RTX 4060 Ti 8GB8 GBFitsQ4_K_M6.6 GB49details
RTX 4070 Super12 GBFitsQ8_010.0 GB53details
RTX 4070 Ti12 GBFitsQ8_010.0 GB53details
RTX 4070 Ti Super16 GBFitsQ8_010.0 GB70details
RTX 408016 GBFitsQ8_010.0 GB75details
RTX 4080 Super16 GBFitsQ8_010.0 GB77details
RTX 50608 GBFitsQ4_K_M6.6 GB76details
RTX 507012 GBFitsQ8_010.0 GB70details
RTX 508016 GBFitsQ8_010.0 GB101details
2x RTX 30902×24 GBFitsF1617.8 GB52details
2x RTX 40902×24 GBFitsF1617.8 GB56details
2x RTX 50902×32 GBFitsF1617.8 GB100details
RTX A600048 GBFitsF1617.8 GB43details
RTX 6000 Ada48 GBFitsF1617.8 GB54details
RTX PRO 6000 Blackwell96 GBFitsF1617.8 GB100details
L40S48 GBFitsF1617.8 GB48details
A100 40GB40 GBFitsF1617.8 GB87details
A100 80GB80 GBFitsF1617.8 GB114details
H100 PCIe80 GBFitsF1617.8 GB112details
H100 SXM80 GBFitsF1617.8 GB187details
H200141 GBFitsF1617.8 GB268details
RX 76008 GBFitsQ4_K_M6.6 GB49details
RX 7700 XT12 GBFitsQ8_010.0 GB45details
RX 7800 XT16 GBFitsQ8_010.0 GB65details
RX 7900 GRE16 GBFitsQ8_010.0 GB60details
RX 7900 XT20 GBFitsQ8_010.0 GB84details
RX 907016 GBFitsQ8_010.0 GB67details
RX 9070 XT16 GBFitsQ8_010.0 GB67details
Ryzen AI Max+ 395 128GB128 GBFitsF1617.8 GB14details
Arc A770 16GB16 GBFitsQ8_010.0 GB59details
Mac M1 16GB16 GBFitsQ6_K8.3 GB8.8details
Mac M2 24GB24 GBFitsQ8_010.0 GB10details
Mac M3 24GB24 GBFitsQ8_010.0 GB10details
Mac M4 16GB16 GBFitsQ6_K8.3 GB16details
Mac M4 32GB32 GBFitsF1617.8 GB6.7details
Mac M1 Pro 32GB32 GBFitsF1617.8 GB11details
Mac M3 Pro 36GB36 GBFitsF1617.8 GB8.4details
Mac M4 Pro 24GB24 GBFitsQ8_010.0 GB29details
Mac M4 Pro 64GB64 GBFitsF1617.8 GB15details
Mac M1 Max 64GB64 GBFitsF1617.8 GB22details
Mac M2 Max 96GB96 GBFitsF1617.8 GB22details
Mac M3 Max 128GB128 GBFitsF1617.8 GB22details
Mac M4 Max 64GB64 GBFitsF1617.8 GB30details
Mac M2 Ultra 192GB192 GBFitsF1617.8 GB45details
Mac M3 Ultra 256GB256 GBFitsF1617.8 GB46details

Questions

How much VRAM does Ornith 1.5 9B need?

About 6.6 GB at 4-bit (Q4_K_M) with an 8K context: 5.5 GB of weights (real GGUF file size), 0.3 GB of KV cache and 0.9 GB of runtime overhead. At 8-bit it needs about 10.0 GB.

What is the smallest GPU that runs Ornith 1.5 9B?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 4060 (8 GB).

Can I run Ornith 1.5 9B on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M1 16GB 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 35B A3B

36B · 21.4 GB at 4-bit

Ornith 1.5 122B

125B · 72.3 GB at 4-bit

Qwen3.5 9B

9.7B · 6.4 GB at 4-bit

Qwen3.5 9B Base

9.7B · 6.4 GB at 4-bit

SenseNova Loop 9B Preview

9.7B · 6.4 GB at 4-bit

MiMo V2.6 Distill Qwen 9B

9.4B · 6.6 GB at 4-bit

Model facts

Hugging Face repoornith-ai/Ornith-1.5-9B
Parameters9,653,104,368 (9.7B)
Layers / hidden size32 / 4096
AttentionGQA (hybrid: 24 linear/state layers); 16 heads, 4 KV heads, head dim 256
KV cache per token (FP16)32.0 KiB
Max context262,144 tokens
Licensemit
Released on HFAug 18, 2026
Downloads (30d) / likes577,186 / 420

Sources: Hugging Face model API · config.json (ornith-ai/Ornith-1.5-9B) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.