LocalLLMChecker

Desktop GPU · NVIDIA

What AI models can a GeForce RTX 3080 10GB run?

10 GB is the point where local models stop being a demo. The popular 7B to 14B models fit with room for a real conversation, and a 32B fits if you accept a lower quantization. At 760 GB/s there is enough bandwidth to keep generation responsive for anything that fits.

Memory10 GB
Bandwidth760 GB/s
Usable for a model9.2 GB
Runtime backendCUDA
ArchitectureAmpere
Power320 W

The short answer

Assuming an 8k context window and default settings, these are the models worth downloading first.

Best all-rounder

Qwen3.5 9B

Q6_K · 7.3 GB · about 81.1 tokens/s

Best for code

Qwen2.5 Coder 14B Instruct

IQ4_XS · 8.86 GB · about 66.4 tokens/s

Largest that still runs well

Qwen3 14B

14.77B parameters · IQ4_XS · about 68.4 tokens/s

Fastest useful answer

DeepSeek Coder V2 Lite Instruct

about 205.9 tokens/s · 8.24 GB

See how fast it feels

GeForce RTX 3080 10GB running Qwen3.5 9B at Q6_K

Wait for the first word219 ms
Then writes at81.1 tok/s
Whole answer2.4 s

YouWhy does my model use more memory when the conversation gets longer?

Model

Simulated from our estimate at a 512-token question, not a recording. Assumes nothing else is competing for the GPU.

Where it sits

With 10 GB it belongs to the 8 GB tier. The 8 GB guide explains what that tier runs and where it runs out, and the bandwidth guide explains why 760 GB/s decides how fast it answers.

Our indicative price for this card is $350 used, reviewed 2026-09-01. That is 2.9 GB of memory and 217 GB/s of bandwidth for every $100. Prices move, so treat these as a place to start a search and not a quote.

Devices in a similar price band, fastest memory first:

DevicePriceMemoryBandwidthBest all-round pick
GeForce RTX 3080 12GB $400 used 12 GB 912 GB/s Gemma 4 12B Instruct, 64.2 t/s
GeForce RTX 3070 Ti $300 used 8 GB 608 GB/s Qwen3.5 9B, 74.4 t/s
Arc A770 16GB $280 used 16 GB 560 GB/s Qwen3.5 27B, 23.1 t/s
Radeon RX 6900 XT $400 used 16 GB 512 GB/s Qwen3.5 27B, 23.2 t/s

Every model, scored on this device

Each row uses the highest-quality quantization that both fits and stays conversational. Speed is a single-stream estimate at 8k context.

Model Params Verdict Download Memory used Speed Max context
Qwen3.5 9B
Qwen 		9.65B Runs great Q6_K 7.3 GB 81.1 t/s 64k
Gemma 4 12B Instruct
Gemma 		11.96B Just fits Q4_K_M 8.44 GB 69.6 t/s 8k
Gemma 4 E4B Instruct
Gemma 		8B Just fits Q8_0 8.42 GB 69.4 t/s 32k
Qwen3 8B
Qwen 		8.19B Just fits Q8_0 9.02 GB 64.9 t/s 8k
Qwen3 14B
Qwen 		14.77B Just fits IQ4_XS 8.61 GB 68.4 t/s 8k
Granite 4.1 8B
Granite 		8.79B Just fits Q6_K 8.37 GB 70.2 t/s 8k
Qwen2.5 VL 7B Instruct
Qwen 		8.29B Just fits Q8_0 8.49 GB 69 t/s 16k
Qwen2.5 14B Instruct
Qwen 		14.77B Just fits IQ4_XS 8.86 GB 66.4 t/s 8k
Qwen2.5 Coder 14B Instruct
Qwen 		14.77B Just fits IQ4_XS 8.86 GB 66.4 t/s 8k
Gemma 3 12B Instruct
Gemma 		12.19B Runs great Q4_K_M 8.07 GB 72.9 t/s 16k
Phi 4
Phi 		14.66B Just fits IQ4_XS 9 GB 65.3 t/s 8k
Qwen2.5 7B Instruct
Qwen 		7.62B Runs great Q8_0 7.83 GB 75.2 t/s 32k
Llama 3.1 8B Instruct
Llama 		8.03B Just fits Q8_0 8.83 GB 66.4 t/s 8k
Qwen2.5 Coder 7B Instruct
Qwen 		7.62B Runs great Q8_0 7.83 GB 75.2 t/s 32k
Mistral Nemo Instruct 2407
Mistral 		12.25B Just fits Q4_K_M 8.2 GB 72.1 t/s 8k
Internlm3 8B Instruct
InternLM 		8.8B Just fits Q8_0 8.97 GB 65.3 t/s 8k
Mistral 7B Instruct V0.3
Mistral 		7.25B Just fits Q8_0 8.45 GB 69.5 t/s 8k
OLMo 3 7B Instruct
OLMo 		7.3B Runs great Q6_K 8.17 GB 72 t/s 16k
Gemma 2 9B Instruct
Gemma 		9.24B Just fits Q5_K_M 8.48 GB 69.1 t/s 8k
Gemma 4 E2B Instruct
Gemma 		5.12B Runs great Q8_0 5.44 GB 109.2 t/s 128k
Qwen3.5 4B
Qwen 		4.66B Runs great Q8_0 5.27 GB 113.9 t/s 128k
Mistral 7B Instruct V0.2
Mistral 		7.24B Just fits Q8_0 8.44 GB 69.6 t/s 8k
DeepSeek Coder 7B Instruct V1.5
DeepSeek 		6.91B Just fits Q6_K 9.11 GB 64.2 t/s 4k
DeepSeek Coder V2 Lite Instruct
DeepSeek 		15.71B (2.74B active) Just fits IQ4_XS 8.24 GB 205.9 t/s 32k
LFM2.5 8B A1B
Liquid 		8.47B (1.57B active) Just fits Q8_0 8.81 GB 196.9 t/s 32k
Qwen3 4B
Qwen 		4.02B Runs great Q8_0 5.46 GB 109.6 t/s 32k
DeepSeek Coder 6.7B Instruct
DeepSeek 		6.74B Just fits Q5_K_M 8.78 GB 66.7 t/s 8k
Gemma 3 4B Instruct
Gemma 		4.3B Runs great Q8_0 4.91 GB 122.8 t/s 128k
Phi 4 Mini Instruct
Phi 		3.84B Runs great Q8_0 5.17 GB 116.5 t/s 32k
Granite 4.1 3B
Granite 		3.4B Runs great Q8_0 4.34 GB 140.2 t/s 64k
Show the other 56 models
Qwen2.5 3B Instruct 3.09B Runs great Q8_0 3.68 GB 167.5 t/s 32k
Phi 3 Mini 4k Instruct 3.82B Runs great Q8_0 4.8 GB 126.2 t/s 4k
Qwen3.5 27B 27.78B Fits only at 2 to 3 bits IQ2_XXS 7.44 GB 79.9 t/s 32k
Llama 3.2 3B Instruct 3.21B Runs great Q8_0 4.42 GB 138 t/s 32k
LFM2.5 2.6B 2.7B Runs great Q8_0 3.14 GB 199.9 t/s 128k
Qwen3.5 2B 2.27B Runs great Q8_0 2.7 GB 237.1 t/s 256k
Gemma 3 27B Instruct 27.43B Fits only at 2 to 3 bits IQ2_XXS 8.11 GB 73 t/s 16k
Gemma 2 2B Instruct 2.61B Runs great Q8_0 3.54 GB 175.2 t/s 8k
Starcoder2 3B 3.03B Runs great Q8_0 3.34 GB 188.5 t/s 16k
Qwen3 1.7B 2.03B Runs great Q8_0 3.22 GB 193.9 t/s 32k
Mistral Small 24B Instruct 2501 23.57B Fits only at 2 to 3 bits IQ2_XXS 7.18 GB 82.9 t/s 16k
Codestral 22B V0.1 22.25B Fits only at 2 to 3 bits IQ2_XXS 7.51 GB 79.5 t/s 8k
DeepSeek R1 Distill Qwen 1.5B 1.78B Runs great Q8_0 2.07 GB 319.7 t/s 128k
Qwen2.5 1.5B Instruct 1.54B Runs great Q8_0 2.06 GB 320.9 t/s 32k
SmolLM2 1.7B 1.71B Runs great Q8_0 3.53 GB 175.2 t/s 8k
OLMo 2 0425 1B 1.48B Runs great Q8_0 2.6 GB 247.3 t/s 4k
Llama 3.2 1B Instruct 1.24B Runs great Q8_0 1.82 GB 378.6 t/s 128k
LFM2.5 1.2B Instruct 1.17B Runs great Q8_0 1.46 GB 499.8 t/s 64k
Gemma 3 1B Instruct 1B Runs great Q8_0 1.35 GB 538.3 t/s 32k
Qwen3.5 0.8B 0.87B Runs great Q8_0 1.28 GB 574.8 t/s 256k
Qwen3 0.6B 0.75B Runs great Q8_0 1.92 GB 345.8 t/s 32k
Qwen2.5 0.5B Instruct 0.49B Runs great Q8_0 0.88 GB 966.4 t/s 32k
LFM2.5 350M 0.35B Runs great Q8_0 0.68 GB 1496.4 t/s 64k
Qwen3.5 35B A3B 35.95B Partial offload n/a 20.48 GB 64.5 t/s n/a
GPT OSS 20B 20.91B Partial offload n/a 11.55 GB 64.2 t/s n/a
Gemma 4 26B A4B Instruct 25.81B Partial offload n/a 15.7 GB 46.9 t/s n/a
GLM 4.7 Flash 31.22B Partial offload n/a 18.13 GB 41.7 t/s n/a
Qwen3 30B A3B 30.53B Partial offload n/a 18.08 GB 41 t/s n/a
Qwen3 Coder 30B A3B Instruct 30.53B Partial offload n/a 18.08 GB 41 t/s n/a
Qwen3 Coder Next 79.67B Partial offload n/a 45.22 GB 36.9 t/s n/a
Qwen3 Next 80B A3B Instruct 81.32B Partial offload n/a 46.15 GB 36.1 t/s n/a
GPT OSS 120B 116.83B Partial offload n/a 59.4 GB 17.7 t/s n/a
Qwen3.5 122B A10B 125.09B Partial offload n/a 70.61 GB 13.9 t/s n/a
Phi 3.5 MoE Instruct 41.87B Partial offload n/a 24.87 GB 13.5 t/s n/a
GLM 4.5 Air 110.47B Partial offload n/a 63.61 GB 7.7 t/s n/a
MiniMax M2.5 228.7B Partial offload n/a 130.56 GB 7.2 t/s n/a
MiniMax M2.7 228.69B Partial offload n/a 130.55 GB 7.2 t/s n/a
Mixtral 8x7B Instruct V0.1 46.7B Partial offload n/a 27.59 GB 6.1 t/s n/a
MiniMax M3 427.04B Partial offload n/a 240.84 GB 3.8 t/s n/a
Qwen3 235B A22B 235.09B Partial offload n/a 133.71 GB 3.6 t/s n/a
Granite 4.1 30B 28.87B Partial offload n/a 18.64 GB 2.9 t/s n/a
Qwen3 32B 32.76B Partial offload n/a 20.42 GB 2.6 t/s n/a
Qwen2.5 32B Instruct 32.76B Partial offload n/a 20.42 GB 2.6 t/s n/a
Qwen2.5 Coder 32B Instruct 32.76B Partial offload n/a 20.42 GB 2.6 t/s n/a
Gemma 4 31B Instruct 31.27B Partial offload n/a 21.31 GB 2.4 t/s n/a
GLM 5.1 753.86B Partial offload n/a 424.51 GB 2.2 t/s n/a
DeepSeek V3.2 685.4B Partial offload n/a 385.91 GB 1.4 t/s n/a
DeepSeek R1 684.53B Partial offload n/a 385.42 GB 1.4 t/s n/a
GLM 4.5 358.34B Partial offload n/a 204.37 GB 1.4 t/s n/a
GLM 5.2 753.33B Partial offload n/a 424.21 GB 1 t/s n/a
Qwen2.5 VL 72B Instruct 73.41B Partial offload n/a 43.62 GB 0.9 t/s n/a
Qwen2.5 72B Instruct 72.71B Partial offload n/a 43.22 GB 0.9 t/s n/a
Llama 3.3 70B Instruct 70.55B Partial offload n/a 42.12 GB 0.9 t/s n/a
Llama 3 3 Nemotron Super 49B V1 49.87B Partial offload n/a 47.99 GB 0.8 t/s n/a
Kimi K2.6 1026.88B Will not run n/a 577.78 GB 1.3 t/s n/a
Kimi K2 Instruct 1026.41B Will not run n/a 577.52 GB 1.3 t/s n/a

What it will not run

2 of the 86 architectures we track are out of reach here, even at 2-bit precision. Another 31 run by splitting the model between the card and system RAM, which works but drops generation to single digits for most dense models.

If you want more headroom

The next steps up in memory, in order. More memory changes which models load at all; more bandwidth changes how fast they answer, so the two are worth weighing separately.

DeviceMemoryBandwidthModels that fit
GeForce RTX 2080 Ti 11 GB 616 GB/s 57 Check price
GeForce GTX 1080 Ti 11 GB 484 GB/s 57 Check price
GeForce RTX 3080 Ti 12 GB 912 GB/s 57 Check price
GeForce RTX 3080 12GB 12 GB 912 GB/s 57 Check price

Price links go to an Amazon search for the model name and are affiliate links: if you buy through one, we earn a commission at no cost to you. We do not take payment for placement, and the ordering above is by memory capacity alone.

Other devices with 10 GB

Same capacity, different speed. Once a model fits, bandwidth is what separates these.

Arc B570

380 GB/s · Intel

Questions people ask about an RTX 3080 10GB

How much VRAM does a GeForce RTX 3080 10GB have?

The GeForce RTX 3080 10GB has 10 GB of VRAM, of which roughly 9.2 GB is available to a model once the operating system takes its share.

Can a GeForce RTX 3080 10GB run a 70B model?

Only partially. About 48 of 48 layers fit on the card and the rest run on the CPU, which brings generation down to roughly 36.9 tokens per second.

What is the best local model for a GeForce RTX 3080 10GB?

Qwen3.5 9B at Q6_K is the strongest all-round fit: 7.3 GB used, around 81.1 tokens per second at 8k context.