Tiny Olmo3ForCausalLM — Hardware Requirements & GPU Compatibility
Chat
Tiny Olmo3ForCausalLM is a 2M-parameter open language model from trl-internal-testing in the OLMo family. It supports a context window of up to 65,536 tokens. At BF16 it needs about 0.30 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 64K)Best on 24 GB (BF16 · ~2184 tok/s · 64K)Macs from 32 GB (~280 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Tiny Olmo3ForCausalLM
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve trl-internal-testing/tiny-Olmo3ForCausalLM --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (11 GB headroom) · BF16
- Generation speed
- ~780 tok/s
- generation speed
- Cost per 1M output tokens
- $0.025
- per 1M output tokens
How Much VRAM Does Tiny Olmo3ForCausalLM Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.3 GB | 0.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 64K context · ~2184 tok/s |
Selected BF16
Brain floating point 160.3GBat 16K context
- Weights
- 0.1 GB
- KV cache
- 0.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.7 GB free · ~2184 tok/s
≥50 tok/s needs ≥23 GB/s · RTX 5090 ~3883, RTX 3090 Ti ~2184
Which Hardware Can Run Tiny Olmo3ForCausalLM?
BF16 · 0.3 GBTiny Olmo3ForCausalLM (BF16) requires 0.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 176 devices with unified memory can run Tiny Olmo3ForCausalLM, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
≤ 11 GB
≤ 11 GB tier →fits · 7.7 GB free · up to 64K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~1647Simulate output on RTX 3080RTX 2080 Ti~1335Simulate output on RTX 2080 TiRTX 3070 Ti~1318Simulate output on RTX 3070 TiM3*8 GB~239Simulate output on iMac 24" M3 (8 GB)Orin Nano~221Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~159Simulate output on iPhone 1720 GB
fits · 19.7 GB free · up to 64K ctx
1 GPU
RX 7900 XT~1600Simulate output on RX 7900 XT32–40 GB
fits · 31.7 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~3883Simulate output on RTX 5090M5 Max36 GB~1073Simulate output on Mac Studio M5 Max (36 GB)M532 GB~358Simulate output on MacBook Air 13" M5 (32 GB)Orin~444Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~293Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Alternatives to Tiny Olmo3ForCausalLM
OLMo family · 20 models →Specifications
- Publisher
- trl-internal-testing
- Family
- OLMo
- Parameters
- 2M
- Architecture
- Olmo3ForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 100,278
- Release Date
- 2026-06-06
Frequently Asked Questions
How much VRAM does Tiny Olmo3ForCausalLM need?
Tiny Olmo3ForCausalLM requires 0.3 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 2M × 16 bits ÷ 8 = 0 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 0.3 GB (at full 66K context)
VRAM usage by quantization
Can I run Tiny Olmo3ForCausalLM on a Mac?
Yes — Mac Mini M1 (8 GB) and 155 other Macs can run Tiny Olmo3ForCausalLM. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 0.3 GB of usable unified memory (RAM minus macOS overhead).
Can I run Tiny Olmo3ForCausalLM locally?
Yes — Tiny Olmo3ForCausalLM can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Tiny Olmo3ForCausalLM?
At BF16, Tiny Olmo3ForCausalLM can reach ~16000 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~2184 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 0.3 × 0.65 = ~17333 tok/s
Estimated speed at BF16 (0.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Tiny Olmo3ForCausalLM?
At BF16, the download is about 0.01 GB.
Which GPUs can run Tiny Olmo3ForCausalLM?
52 consumer GPUs can run Tiny Olmo3ForCausalLM at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Tiny Olmo3ForCausalLM?
176 devices with unified memory can run Tiny Olmo3ForCausalLM at BF16 (0.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.