What LLMs fit in 8GB VRAM? (Oct 2026)
7 models on our list fit in 8 GB of graphics memory. The largest by parameter count is DeepSeek R1 Distill Qwen 14B at IQ2_XS, 7.11 GB (measured weights; total is an estimate). We keep 0.6 GB free on one graphics card, so 7.4 GB is usable. Each total adds conversation memory for 8,192 tokens (or the model's own maximum, when that is shorter) and 0.8 GB for the software. The total is an estimate.
Updated
Own a 8 GB GPU? Get a 1-line alert when a new top model fits 7.4 GB usable VRAM
7 models on our catalog fit 8 GB today. Get our weekly 1-line alert when a new open-weight LLM lands inside 7.4 GB at Q4_K_M or when 8 GB+ GPU prices drop >10% — zero spam.
Models that fit
Ranked by parameter count, largest first. The best quant is the highest-quality option that fits in 7.4 GB. A measured download is used when we have one. Otherwise the figure is Q4, Q5, Q8 or FP16 from our estimate. The gigabytes are the weights plus conversation memory for 8,192 tokens, or the model's shorter maximum, plus 0.8 GB for the software. The total is an estimate.
| Rank | AI model | Parameters | Best quant | GB | Label |
|---|---|---|---|---|---|
| 1 | Can I run DeepSeek R1 Distill Qwen 14B? | 14.77B | IQ2_XS | 7.11 GB | measured weights; total is an estimate |
| 2 | Can I run Llama 3.1 8B? | 8.03B (estimate) | Q4_K_M | 6.69 GB | estimate |
| 3 | Can I run NVIDIA Nemotron 3.5 Bolt E4B? | 8B (estimate) | UD-Q5_K_XL | 6.90 GB | measured weights; total is an estimate |
| 4 | Can I run Mistral 7B v0.3? | 7.25B (estimate) | Q5 (~0.71 bytes/param) | 7.02 GB | estimate |
| 5 | Can I run Spark-X2.6-4B? | 4.11B (estimate) | Q8_0 | 5.54 GB | measured weights; total is an estimate |
| 6 | Can I run Llama 3.2 3B? | 3.21B (estimate) | Q8 | 5.17 GB | estimate |
| 7 | Can I run LFM3-1.7B? | 1.73B (estimate) | BF16 | 4.38 GB | measured weights; total is an estimate |
LFM3-1.7B, Spark-X2.6-4B and Nemotron 3.5 Bolt E4B on 8 GB
Totals add the measured file, conversation memory at 8,192 tokens, and 0.80 GB of working space. File sizes are measured. The totals and the speeds are our estimate.
| Model | Parameters | Architecture | Conversation memory | Q4_K_M file to total | BF16 file to total | Max context | Minimum hardware for Q4_K_M |
|---|---|---|---|---|---|---|---|
| LFM3-1.7B | 1.73B dense, our estimate. | 24 layers: 13 gated short convolutions, 5 sliding-window (256), 6 global attention. | 0.11 GB | 1.10 GB measured GGUF → 2.01 GB (0.97 GB MLX → 1.88 GB) | 3.47 GB → 4.38 GB. Fits an 8 GB GPU (7.4 GB usable). | 262,144 | Phone or laptop CPU, or a 4 GB GPU (3.4 GB usable). About 222 tok/s on GeForce RTX 3060 12GB, our estimate. Mac mini M4 16GB, about 47 tok/s, our estimate. |
| Spark-X2.6-4B | 4.11B dense, our estimate. | 36 layers: 27 sliding-window (512) and 9 full attention. | 0.36 GB | 2.62 GB measured GGUF → 3.78 GB. Official Q4_K_M 3.54 GB → 4.70 GB | 8.23 GB → 9.39 GB. Fits a 12 GB GPU (11.4 GB usable). | 1,048,576 | 6 GB GPU (5.4 GB usable) or an 8 GB Mac (5.3 GB usable). About 93 tok/s on GeForce RTX 3060 12GB, our estimate. |
| NVIDIA Nemotron 3.5 Bolt E4B | 8B parameters, our estimate. The card calls 4B of that effective, from per-layer embeddings. | 42 layers: 35 sliding-window (512) and 7 full attention. | 0.27 GB | 6.18 GB measured GGUF → 7.25 GB (4.20 GB MLX → 5.27 GB) | 15.05 GB → 16.12 GB. Fits a 24 GB GPU (23.4 GB usable). | 65,536. The GGUF header and Ollama list 128K. | 8 GB GPU (7.4 GB usable) or a 16 GB Mac (10.7 GB usable). About 43 tok/s on GeForce RTX 3060 12GB, our estimate. |
Cards and Macs with 8 GB
No graphics card or Mac on our list has 8 GB.
Memory totals are our estimate, including when the weight file was measured. Prices are the euro figures we store, with the date they were written down. How we calculate
Common questions
- What is the largest model that fits in 8 GB of VRAM?
- DeepSeek R1 Distill Qwen 14B is the largest by parameter count, at IQ2_XS, 7.11 GB (measured weights; total is an estimate). 7 models on our list fit.
- What does the best quant mean for 8 GB?
- The best quant is the highest-quality option that still fits. A measured download is used when we have one at that quality. Otherwise the figure is Q4, Q5, Q8 or FP16 from our estimate. A higher bit count wins. A file that runs only on a Mac is not counted. The gigabytes add conversation memory and the software overhead, so the total is an estimate even when the weight file was measured.
- Which cards and Macs have 8 GB, and what do they cost in the EU?
- No graphics card or Mac on our list has 8 GB. The model table is still for one graphics card of that size.
- How much of 8 GB can a model use?
- Our estimate keeps 0.6 GB free on one graphics card, so 7.4 GB is usable. A Mac with 8 GB of shared memory does not give the graphics all of it. The model table is for one graphics card.