OLMo 2 7B Instruct
7BAllen AI OLMo
⚠ Superseded · Prefer OLMo 3 7B Instruct
This index would suggest OLMo 3 7B Instruct instead today — longer context (4K → 64K tokens). The numbers below are still accurate; they are just for a model you probably should not start with. Compare the two →
Fully open training pipeline from Allen AI. Great for reproducibility research.
4K
Max Context
2
Quant Variants
GGUF Q8_0
Best Quality
+0.3%
Perplexity rise (best build)
Quantization Variants
Per-quant VRAM, quality loss, and inference speed on RTX 4090
Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports
| Format | Level | BPW | VRAM | PPL Loss | Speed | Source | Actions |
|---|---|---|---|---|---|---|---|
| GGUF | Q4_K_M | 4.85 | 6.8 GB | 3.4% | 150 tok/s | Estimated | |
| GGUF | Q8_0 | 8.5 | 10.3 GB | 0.3% | 125 tok/s | Estimated |
Which file each size is for
A file size is not a memory figure: the VRAM column is the calculator's total at 4K context — weights plus KV cache plus a 10% activation buffer. Units differ on purpose: file sizes are decimal GB, as Hugging Face lists them; the VRAM column is GiB (1024³ bytes) with 2% added to the weights, so 7.12 GB of file counts as about 6.8 GiB there. A vision projector (mmproj), where the repo ships one, is a separate download and is in neither number.
- GGUF Q4_K_MSized at the calculator's generic rate for this level; no file was checked.
- GGUF Q8_0Sized at the calculator's generic rate for this level; no file was checked.
Similar models
Compare with OLMo 3OLMo 3 7B Instruct
Allen AI OLMo
Allen AI's fully open 7B model, released with its training data, code and intermediate checkpoints. Its predecessor stopped at a 4K context; OLMo 3 reaches 64K, extended from an 8K base by YaRN. Three of every four layers use a 4K sliding window, which is what makes that affordable. It still uses full multi-head attention with no shared KV heads, so long context costs more here than on most 7B–8B models. At Q4_K_M it needs about 6.8 GB at 4K context and 10.9 GB at 32K. Without the sliding window, 32K would need about 22 GB. Sizes use the calculator's generic rates, since no GGUF file size could be checked, and no per-level quality loss has been published.
Llama 3.1 8B Instruct
Meta Llama 3.1
Meta's flagship 8B model with 128K context. Best-in-class for local deployment.
Qwen2.5 7B Instruct
Alibaba Qwen2.5
Alibaba's highly optimized 7B. Punches well above its weight, especially in coding.
Phi-3.5 Mini Instruct
Microsoft Phi
Microsoft's tiny powerhouse. Best 4B model for on-device deployment.
Running OLMo 2 7B Instruct locally
At Q4_K_M and 4K of context, OLMo 2 7B Instruct needs about 6.8 GB — 4.2 GB of weights, 2.00 GB of KV cache and a 0.6 GB activation buffer. The smallest cards in this index that clear that comfortably are 8 GB ones — 9 of them, from the RTX 4060 up — and 76 of the 78 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.
What longer context costs
Going from 4K to 32K adds about 14.00 GB, taking the total to 22.2 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 4K; holding all of it at Q4_K_M would need about 7 GB.
Which build to download
This index only tracks OLMo 2 7B Instruct in GGUF, across 2 levels (Q4_K_M, Q8_0). Q8_0 carries the lowest published perplexity loss at 0.3%. The fastest level listed is Q4_K_M at about 150 tok/s on an RTX 4090, batch 1 — an estimate, not a run on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving.
Common questions
- How much VRAM does OLMo 2 7B Instruct need?
- About 6.8 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 22.2 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
- Will OLMo 2 7B Instruct run on a 8GB GPU?
- Yes — at Q4_K_M and 4K context it needs about 6.8 GB, which leaves 1.2 GB spare on a RTX 4060, or on any of the other 8 GB cards here (9 in all). That is the smallest size in this index that clears it comfortably; 76 of 78 do.
- Which quantization of OLMo 2 7B Instruct should I use?
- Q8_0 has the lowest published quality loss (0.3%), and Q4_K_M is the level most people run. All 2 levels in the index are Q4_K_M, Q8_0.
Where this model fits
Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.
- Runs comfortably on
- RTX 40608GB · +1.2RTX 4060 Ti 8G8GB · +1.2Radeon RX 9060 XT 8G8GB · +1.2RTX 5060 Ti 8G8GB · +1.2RTX 50608GB · +1.2
- Just misses
- Mac M1 8G+0.8GB overMac M3 8G+0.8GB over
- Ships in
- GGUF
- Try it yourself
- Size it in the calculatorGenerate the run command
How to actually run this
Deployment guides for this model and this class of hardware.
This page's figures change when the model or the runtime does.Last updated 2026-11-07 RSS → /feed.xml