What Models?

Pick the right model for your GPU — in seconds.

What AI models can an RTX 3080 (10 GB) run?

The GeForce RTX 3080 has 10 GB of VRAM and 760 GB/s memory bandwidth. 31 models run well on it and 8 more are a tight fit.

Fine-tune for your setup (context, speed, system RAM, multiple GPUs) → Check price on Amazon

As an Amazon Associate, I earn from qualifying purchases.

Best for general use

Highest MMLU score among models that run well

  1. Qwen3.5 9B Q8_0 36K context · ~77 tok/s · MMLU 82.5
  2. Qwen3.5 4B Q8_0 188K context · ~147 tok/s · MMLU 79.1
  3. Qwen3 8B Q4_K_M 36K context · ~126 tok/s · MMLU 79

Best for coding

Highest SWE-bench Verified score among models that run well

  1. K2-Horizon 7B Q4_K_M 34K context · ~122 tok/s · SWE-bench 70.6
  2. Ornith 1.5 9B Q8_0 28K context · ~75 tok/s · SWE-bench 70.6
  3. MiMo V2.6 Distill Qwen 9B Q8_0 35K context · ~77 tok/s · SWE-bench 61.1

Upgrade options

The cheapest GPUs with more VRAM than the RTX 3080, by launch MSRP.

As an Amazon Associate, I earn from qualifying purchases.

Every model on the RTX 3080

68 of 200 model configurations can run on 10 GB — sorted by quality

100 models, each counted once by the best way it runs on your hardware.

Largest that runs well Nemotron Nano 12B 12.6B params · Q4_K_M · 114K context
Fastest good-quality model Phi-3 Mini 3.8B ~224 tok/s · Q4_K_M · 20K context
? MMLU (Massive Multitask Language Understanding) measures general knowledge across 57 subjects. Higher = more capable. Sorted best-first.

Runs well 31

  • Qwen3.5 9B 9B Great VisionTool useReasoning
    MMLU 82.5
    Q4_K_M
    Context 151K Speed ~121 tok/s
    Q8_0
    Context 36K Speed ~77 tok/s
  • Qwen3.5 4B 4B Great VisionTool useReasoning
    MMLU 79.1
    Q4_K_M
    Context 240K Speed ~214 tok/s
    Q8_0
    Context 188K Speed ~147 tok/s
  • Qwen3 8B 8.2B Great ReasoningTool use
    MMLU 79
    Q4_K_M
    Context 36K Speed ~126 tok/s
    Q8_0 Tight fit · 9K context

Runs well 31

  • Qwen3.5 9B 9B Great VisionTool useReasoning
    MMLU 82.5
    Q4_K_M
    Context 151K Speed ~121 tok/s
    Q8_0
    Context 36K Speed ~77 tok/s
  • Qwen3.5 4B 4B Great VisionTool useReasoning
    MMLU 79.1
    Q4_K_M
    Context 240K Speed ~214 tok/s
    Q8_0
    Context 188K Speed ~147 tok/s
  • Qwen3 8B 8.2B Great ReasoningTool use
    MMLU 79
    Q4_K_M
    Context 36K Speed ~126 tok/s
    Q8_0 Tight fit · 9K context
  • Gemma 4 12B 11.96B Great VisionTool useReasoning
    MMLU 77.2
    Q4_K_M
    Context 224K Speed ~100 tok/s
    Q8_0 Doesn't fit · needs 11.8 GB
  • Nemotron Nano 12B 12.6B Great ReasoningTool use
    MMLU 76
    Q4_K_M
    Context 114K Speed ~91 tok/s
    Q8_0 Doesn't fit · needs 13.1 GB
  • Qwen 2.5 7B 7.62B Good Tool use
    MMLU 74.2
    Q4_K_M
    Context 100K Speed ~134 tok/s
    Q8_0
    Context 35K Speed ~84 tok/s
  • Qwen 2.5 VL 7B 7.62B Good VisionTool use
    MMLU 74.2
    Q4_K_M
    Context 100K Speed ~134 tok/s
    Q8_0
    Context 35K Speed ~84 tok/s
  • Gemma 3 12B 11.8B Good Vision
    MMLU 74
    Q4_K_M
    Context 44K Speed ~92 tok/s
    Q8_0 Doesn't fit · needs 12.6 GB
  • Llama 3.2 Vision 11B 10.6B Good VisionTool use
    MMLU 73
    Q4_K_M
    Context 33K Speed ~109 tok/s
    Q8_0 Doesn't fit · needs 10.5 GB
  • Phi-3 Mini 3.8B 3.82B Good
    MMLU 70.9
    Q4_K_M
    Context 20K Speed ~224 tok/s
    Q8_0
    Context 16K Speed ~150 tok/s
  • Phi-4 Mini 3.8B 3.84B Good
    MMLU 70
    Q4_K_M
    Context 61K Speed ~218 tok/s
    Q8_0
    Context 48K Speed ~150 tok/s
  • Gemma 4 E4B 4.5B Good VisionTool useReasoning
    MMLU 69.4
    Q4_K_M
    Context 128K Speed ~126 tok/s
    Q8_0
    Context 128K Speed ~90 tok/s
  • Llama 3.1 8B 8.03B Good Tool use
    MMLU 69.4
    Q4_K_M
    Context 41K Speed ~128 tok/s
    Q8_0 Tight fit · 11K context
    fp16 Doesn't fit · needs 16.2 GB
  • Qwen 2.5 Coder 7B 7.62B Good
    MMLU 68
    Q4_K_M
    Context 100K Speed ~134 tok/s
    Q8_0
    Context 35K Speed ~84 tok/s
  • Qwen 2.5 VL 3B 3.09B Fair Vision
    MMLU 65.6
    Q4_K_M
    Context 128K Speed ~259 tok/s
    Q8_0
    Context 128K Speed ~177 tok/s
  • Qwen 2.5 3B 3.09B Fair Tool use
    MMLU 65.6
    Q4_K_M
    Context 32K Speed ~259 tok/s
    Q8_0
    Context 32K Speed ~177 tok/s
  • Ministral 8B 8.02B Fair Tool use
    MMLU 65
    Q4_K_M
    Context 35K Speed ~125 tok/s
    Q8_0 Tight fit · 10K context
  • SmallThinker 3B 3.09B Fair Reasoning
    MMLU 65
    Q4_K_M
    Context 32K Speed ~259 tok/s
    Q8_0
    Context 32K Speed ~177 tok/s
  • Llama 3.2 3B 3.21B Fair Tool use
    MMLU 63.4
    Q4_K_M
    Context 74K Speed ~252 tok/s
    Q8_0
    Context 61K Speed ~172 tok/s
    fp16
    Context 33K Speed ~102 tok/s
  • Gemma 3 4B 3.88B Fair Vision
    MMLU 63
    Q4_K_M
    Context 128K Speed ~218 tok/s
    Q8_0
    Context 128K Speed ~148 tok/s
  • Gemma 4 E2B 2.3B Fair VisionTool useReasoning
    MMLU 60
    Q4_K_M
    Context 128K Speed ~180 tok/s
    Q8_0
    Context 128K Speed ~135 tok/s
  • DeepSeek R1 Distill Qwen 7B 7.62B Fair Reasoning
    MMLU 58
    Q4_K_M
    Context 100K Speed ~134 tok/s
    Q8_0
    Context 35K Speed ~84 tok/s
  • Qwen3.5 2B 2B Fair VisionTool useReasoning
    MMLU 55.3
    Q4_K_M
    Context 256K Speed ~347 tok/s
    Q8_0
    Context 256K Speed ~265 tok/s
  • Llama 3.2 1B 1.24B Basic Tool use
    MMLU 49.3
    Q4_K_M
    Context 128K Speed ~420 tok/s
    Q8_0
    Context 128K Speed ~328 tok/s
  • Qwen3.5 0.8B 0.8B Basic VisionTool useReasoning
    MMLU 29.7
    Q4_K_M
    Context 256K Speed ~507 tok/s
    Q8_0
    Context 256K Speed ~432 tok/s
  • Nemotron 3 Nano 4B 3.97B Basic ReasoningTool use
    MMLU
    Q4_K_M
    Context 256K Speed ~202 tok/s
    Q8_0
    Context 256K Speed ~154 tok/s
  • Ornith 1.5 9B 9.65B Basic Tool useReasoning
    MMLU
    Q4_K_M
    Context 149K Speed ~119 tok/s
    Q8_0
    Context 28K Speed ~75 tok/s
  • MiMo V2.6 Distill Qwen 9B 9.41B Basic VisionTool useReasoning
    MMLU
    Q4_K_M
    Context 147K Speed ~118 tok/s
    Q8_0
    Context 35K Speed ~77 tok/s
  • LFM2.5 2.6B 2.7B Basic Tool use
    MMLU
    Q4_K_M
    Context 128K Speed ~297 tok/s
    Q8_0
    Context 128K Speed ~207 tok/s
  • Nemotron 3.5 Bolt E4B 8B Basic Tool useReasoning
    MMLU
    Q4_K_M
    Context 64K Speed ~112 tok/s
    Q8_0
    Context 64K Speed ~90 tok/s
  • K2-Horizon 7B 9B Basic Tool useReasoning
    MMLU
    Q4_K_M
    Context 34K Speed ~122 tok/s
    Q8_0 Tight fit · 7K context

Tight fit 8

Tight fit 8

Notify me when new models fit my GPU

An email when a new model fits your RTX 3080 — no spam, unsubscribe anytime.

Doesn't fit 61

  • DeepSeek R1 0528 671B Excellent Reasoning
    MMLU 90.8
    Q4_K_M Needs 409.3 GB — 399.3 GB over
    Q8_0 Needs 713.4 GB — 703.4 GB over
  • Qwen3 Next 80B-A3B 80B Excellent Tool use
    MMLU 90
    Q4_K_M Needs 48.4 GB — 38.4 GB over
    Q8_0 Needs 84.8 GB — 74.8 GB over
    GPUs that can run this

    As an Amazon Associate, I earn from qualifying purchases.

  • MiMo V2.5 Pro 1020B Excellent Reasoning
    MMLU 89.4
    Q4_K_M Needs 630.1 GB — 620.1 GB over
    Q8_0 Needs 1090.1 GB — 1080.1 GB over

Doesn't fit 61