Olmo 3 32B Think SFT — Hardware Requirements & GPU Compatibility
Chat
Olmo 3 32B Think SFT is a 32.2B-parameter open language model from Allen AI in the OLMo family. It supports a context window of up to 65,536 tokens. At Q4_K_M it needs about 20.18 GB of VRAM — see which GPUs and Macs can run it below.
Decent on a 24 GB GPU
Runs from 16 GB (Q2_K · 16K)Best on 24 GB (Q4_K_M · ~33 tok/s · 32K)Macs from 24 GB (Q4_K_M · ~11 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Olmo 3 32B Think SFT
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/mradermacher/Olmo-3-32B-Think-SFT-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 2.5 GB free · 16K context
Download: Olmo-3-32B-Think-SFT.Q4_K_M.gguf19.48 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 5090 (32 GB) (10 GB headroom) · Q4_K_M
- Generation speed
- ~58 tok/s
- generation speed
- Cost per 1M output tokens
- $2.39
- per 1M output tokens
How Much VRAM Does Olmo 3 32B Think SFT Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 14.5 GB | 17 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 64K context · ~45 tok/s | |
| 14.9 GB | 17.4 GB | 3-bit small — 3-bit small quantization | Fits: 64K context · ~44 tok/s | |
| 16.6 GB | 19 GB | 3-bit medium — 3-bit medium quantization | Fits: 64K context · ~40 tok/s | |
| 17.4 GB | 19.8 GB | 3-bit large — 3-bit large quantization | Fits: 64K context · ~38 tok/s | |
| 20.2 GB | 22.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~33 tok/s | |
| 23.8 GB | 26.2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 2K context · ~28 tok/s | |
| 27.4 GB | 29.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 28.8 GB | |
| 33.1 GB | 35.5 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 34.4 GB |
Selected Q4_K_M
4-bit medium quantization21.5GBat 16K context
- Weights
- 19.3 GB
- KV cache
- 1.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 2.5 GB free · ~33 tok/s
≥50 tok/s needs ≥1.55 TB/s · RTX 5090 ~58
Which Hardware Can Run Olmo 3 32B Think SFT?
Q4_K_M · 20.2 GBOlmo 3 32B Think SFT (Q4_K_M) requires 20.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 27+ GB is recommended. Using the full 66K context window can add up to 4.6 GB, bringing total usage to 24.7 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Olmo 3 32B Think SFT, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit IQ4_XS (19.5 GB)
1 GPU
RX 7900 XT~26Simulate output on RX 7900 XT32–40 GB
fits · 10.5 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~58Simulate output on RTX 5090M5 Max36 GB~16Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~4Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Olmo 3 32B Think SFT
OLMo family · 20 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Nanbeige4.3 33BNanbeige | — | 23.7 GB | ~32 | same size |
| Hy Memory 30B A3BTencent | — | 19.1 GB | ~184 | same size |
| Granite Switch 4.1 30BIBM | — | 22.7 GB | ~35 | same size |
| Llm Jp 4.1 32B A3b Thinkingllm-jp | — | 20.1 GB | ~188 | same size |
| Llm Jp 4.1 33B Thinkingllm-jp | — | 22.5 GB | ~35 | same size |
| Agnes 3.0 FlashAgnes-AI | — | 22.1 GB | ~35 | same size |
Specifications
- Publisher
- Allen AI
- Family
- OLMo
- Parameters
- 32.2B
- Architecture
- Olmo3ForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 100,278
- Release Date
- 2025-11-14
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Olmo 3 32B Think SFT need?
Olmo 3 32B Think SFT requires 20.2 GB of VRAM at Q4_K_M, or 65.3 GB at BF16. Full 66K context adds up to 4.6 GB (24.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32.2B × 4.8 bits ÷ 8 = 19.3 GB
KV Cache + Overhead ≈ 0.9 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 ≈ 5.4 GB (at full 66K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Olmo 3 32B Think SFT?
Yes, at Q5_K_M (23.8 GB) or lower. Higher quantizations like Q6_K (27.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Olmo 3 32B Think SFT?
For Olmo 3 32B Think SFT, Q4_K_M (20.2 GB) offers the best balance of quality and VRAM usage. Q5_K_S (23 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 14.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Olmo 3 32B Think SFT on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Olmo 3 32B Think SFT. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 20.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run Olmo 3 32B Think SFT locally?
Yes — Olmo 3 32B Think SFT can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Olmo 3 32B Think SFT?
At Q4_K_M, Olmo 3 32B Think SFT can reach ~238 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~33 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 ÷ 20.18 × 0.65 = ~258 tok/s
Estimated speed at Q4_K_M (20.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Olmo 3 32B Think SFT?
At Q4_K_M, the download is about 19.34 GB. The full-precision BF16 version is 64.47 GB. The smallest option (Q2_K) is 13.70 GB.
Which GPUs can run Olmo 3 32B Think SFT?
7 consumer GPUs can run Olmo 3 32B Think SFT at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Olmo 3 32B Think SFT?
122 devices with unified memory can run Olmo 3 32B Think SFT at Q4_K_M (20.2 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.