OLMoE 1B 7B 0924 Instruct — Hardware Requirements & GPU Compatibility
Chat
OLMoE 1B 7B 0924 Instruct is a 6.9B-parameter open language model from Allen AI in the OLMo family. It supports a context window of up to 4,096 tokens. At Q4_K_M it needs about 4.72 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 4K)Best on 24 GB (Q4_K_M · ~452 tok/s · 4K)Macs from 8 GB (Q3_K_L · ~72 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run OLMoE 1B 7B 0924 Instruct
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/bartowski/OLMoE-1B-7B-0924-Instruct-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 19.0 GB free · 4K context
Download: OLMoE-1B-7B-0924-Instruct-Q4_K_M.gguf4.21 GBbartowski
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (7 GB headroom) · Q4_K_M
- Generation speed
- ~217 tok/s
- generation speed
- Cost per 1M output tokens
- $0.088
- per 1M output tokens
How Much VRAM Does OLMoE 1B 7B 0924 Instruct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.5 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 4K context · ~534 tok/s | |
| 3.6 GB | — | 3-bit small — 3-bit small quantization | Fits: 4K context · ~527 tok/s | |
| 3.9 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 4K context · ~502 tok/s | |
| 4.0 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 4K context · ~495 tok/s | |
| 4.7 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 4K context · ~452 tok/s | |
| 5.5 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 4K context · ~411 tok/s | |
| 6.3 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 4K context · ~377 tok/s | |
| 7.5 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 4K context · ~334 tok/s |
Selected Q4_K_M
4-bit medium quantization5.0GBat 4K context
- Weights
- 4.2 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 19.0 GB free · ~452 tok/s
≥50 tok/s needs ≥70 GB/s · RTX 5090 ~613, RTX 3090 Ti ~452
Which Hardware Can Run OLMoE 1B 7B 0924 Instruct?
Q4_K_M · 4.7 GBOLMoE 1B 7B 0924 Instruct (Q4_K_M) requires 4.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 4K context window can add up to 0.3 GB, bringing total usage to 5.0 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 151 devices with unified memory can run OLMoE 1B 7B 0924 Instruct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.0 GB free · up to 4K ctx
16 GPUs · 2 device families
RTX 3080~377Simulate output on RTX 3080RTX 2080 Ti~326Simulate output on RTX 2080 TiRTX 3070 Ti~323Simulate output on RTX 3070 TiOrin Nano~71Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~47Simulate output on iPhone 1720 GB
fits · 15.0 GB free · up to 4K ctx
1 GPU
RX 7900 XT~199Simulate output on RX 7900 XT32–40 GB
fits · 27.0 GB free · up to 4K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~613Simulate output on RTX 5090M5 Max36 GB~169Simulate output on Mac Studio M5 Max (36 GB)M532 GB~88Simulate output on MacBook Air 13" M5 (32 GB)Orin~134Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~87Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to OLMoE 1B 7B 0924 Instruct
OLMo family · 20 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Mathstral 7B v0.1Mistral AI | — | 6.8 GB | ~133 | same size |
| Mistral 7B Instruct v0.3Mistral AI | — | 6.8 GB | ~133 | same size |
| Phi 3 Small 8k InstructMicrosoft | — | 16.2 GB | ~43 | same size |
| CodeQwen1.5 7BAlibaba | — | 5.7 GB | ~137 | same size |
| Starling LM 7B BetaNexusflow | — | 5.7 GB | ~133 | same size |
| Llava 1.5 7B HFllava-hf | — | 5 GB | ~141 | same size |
Specifications
- Publisher
- Allen AI
- Family
- OLMo
- Parameters
- 6.9B
- Active parameters
- 1.3B per token
- Architecture
- OlmoeForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 50,304
- Release Date
- 2024-08-13
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does OLMoE 1B 7B 0924 Instruct need?
OLMoE 1B 7B 0924 Instruct requires 4.7 GB of VRAM at Q4_K_M, or 14.4 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 6.9B × 4.8 bits ÷ 8 = 4.2 GB
KV Cache + Overhead ≈ 0.5 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 ≈ 0.8 GB (at full 4K context)
VRAM usage by quantization
What's the best quantization for OLMoE 1B 7B 0924 Instruct?
For OLMoE 1B 7B 0924 Instruct, Q4_K_M (4.7 GB) offers the best balance of quality and VRAM usage. Q5_0 (4.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 3.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run OLMoE 1B 7B 0924 Instruct on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run OLMoE 1B 7B 0924 Instruct, the smallest at Q3_K_L. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 4.7 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M2 Pro (16 GB).
Can I run OLMoE 1B 7B 0924 Instruct locally?
Yes — OLMoE 1B 7B 0924 Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is OLMoE 1B 7B 0924 Instruct?
At Q4_K_M, OLMoE 1B 7B 0924 Instruct can reach ~296 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~452 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 0.9 GB active ÷ (8000 × 0.65) = 0.168 ms, plus 16 layers × 0.055 ms = 0.880 ms, so 1000 ÷ 1.048 ms = ~954 tok/s
Estimated speed at Q4_K_M (4.7 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of OLMoE 1B 7B 0924 Instruct?
At Q4_K_M, the download is about 4.15 GB. The full-precision BF16 version is 13.84 GB. The smallest option (Q2_K) is 2.94 GB.
Which GPUs can run OLMoE 1B 7B 0924 Instruct?
52 consumer GPUs can run OLMoE 1B 7B 0924 Instruct at Q4_K_M. 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 OLMoE 1B 7B 0924 Instruct?
151 devices with unified memory can run OLMoE 1B 7B 0924 Instruct at Q4_K_M (4.7 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.