Skip to content

Ornith 1.5 35B A3B on 4× RTX 3090: VRAM, speed and fit

Ornith 1.5 35B A3B at 8-bit runs on the 4× RTX 3090 with 256K of context at about 136 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 4× RTX 3090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
43.8 GB
of 96.0 GB
Context
256K
auto
Speed
136 tok/s
64 when full
First reply
0.1 s
2K prompt

Where the memory goes

Model
35.6 GB
Context
5.1 GB
Overhead
3.1 GB
OS
0.0 GB
Free
52.2 GB
Memory
43.8 GB of 96.0 GB
Context
256K tokens · auto
Speed
136 tok/s · 64 when full
First reply
0.1 s for a 2K prompt
Running cost
$20/mo at home · $66/mo on a cloud 2× RTX A5000

Validation: Validated

What Ornith 1.5 35B A3B on 4× RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory96.0 GB usable43.8 GB neededPass
Headroom5% free52.2 GB free (54%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more136 tok/sPass
First replyunder 3 s, 2K prompt0.1 sPass

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Ornith 1.5 35B A3B
Parameters
36B, 3B active
Precision
8-bit (Q8_0)
Context
256K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
4× RTX 3090
GPU can use
96.0 GB of 96.0 GB

Running cost

At home
$20/mo
920 W at the wall
Renting instead
$66/mo
2× RTX A5000 at $0.54/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

llama.cpp
llama-server -hf peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP
vLLM
vllm serve ornith-ai/Ornith-1.5-35B-A3B
MLX (Mac)
mlx_lm.chat --model mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit

Ornith 1.5 35B A3B on similar machines

All machines: Ornith 1.5 35B A3B VRAM requirements. Everything that runs here: what can the 4× RTX 3090 run?

Other models that run on 4× RTX 3090

Questions

Can Ornith 1.5 35B A3B run on 4× RTX 3090?

Ornith 1.5 35B A3B at 8-bit runs on the 4× RTX 3090 with 256K of context at about 136 tokens a second.

Report VR-13JJ9A3, calculated Nov 22, 2026 from published specs, not benchmarked.