Yes — with 44.0 GB to spare
Olmo 3 7B Instruct at Q4_K_M fits your CPU only · DDR5 dual-channel entirely on the GPU at 8K context, at an estimated 9.2 tokens per second. There is room for its full 64K window.
Fully on GPU
8K context
Q4_K_M · 4.1 GB
Apache 2.0
Released 20 Nov 2025
Fully open — training data and code included. Full multi-head attention, so its cache is 4× a GQA 7B at the same context.
The VRAM budget
weights 4.1 GB
Weights 4.1 GB
KV cache @ 8K 2.50 GB
Runtime overhead 0.6 GB
Free 44.0 GB of 51.2 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 13.6 GB | 16.7 GB | 64K | 2.8 | Reference | Long context |
| Q8_0 | 7.2 GB | 10.3 GB | 64K | 5.2 | −0.1% ppl | Long context |
| Q6_K | 5.6 GB | 8.7 GB | 64K | 6.8 | −0.4% ppl | Long context |
| Q5_K_M | 4.8 GB | 7.9 GB | 64K | 7.8 | −0.8% ppl | Long context |
| Q4_K_M | 4.1 GB | 7.2 GB | 64K | 9.2 | −1.9% ppl | Recommended |
| Q3_K_M | 3.3 GB | 6.4 GB | 64K | 11 | −5.4% ppl | Long context |
| Q2_K | 2.8 GB | 5.9 GB | 64K | 13 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (4096 tokens, 8 of 32 layers global), which is why its cache barely grows with context.
How to run it
$ llama-server \
-hf allenai/Olmo-3-7B-Instruct:Q4_K_M \
-c 8192 -ngl 99
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
01Download is 4.1 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02With no GPU, thread count matters more than clock. Start at one thread per physical core.
03There is room to go to the model's full 64K context on this card.