What Models?

Pick the right model for your GPU — in seconds.

What AI models can an RTX A2000 (6 GB) run?

The RTX A2000 has 6 GB of VRAM and 288 GB/s memory bandwidth. 22 models run well on it and 6 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 Q4_K_M 22K context · ~46 tok/s · MMLU 82.5
  2. Qwen3.5 4B Q8_0 59K context · ~56 tok/s · MMLU 79.1
  3. Qwen 2.5 7B Q4_K_M 24K context · ~51 tok/s · MMLU 74.2

Best for coding

Highest SWE-bench Verified score among models that run well

  1. Ornith 1.5 9B Q4_K_M 20K context · ~45 tok/s · SWE-bench 70.6
  2. MiMo V2.6 Distill Qwen 9B Q4_K_M 18K context · ~45 tok/s · SWE-bench 61.1
  3. Qwen 2.5 Coder 7B Q4_K_M 24K context · ~51 tok/s · SWE-bench 14.8

Upgrade options

The cheapest GPUs with more VRAM than the RTX A2000, by launch MSRP.

As an Amazon Associate, I earn from qualifying purchases.

Every model on the RTX A2000

42 of 200 model configurations can run on 6 GB — sorted by quality

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

Largest that runs well Ornith 1.5 9B 9.65B params · Q4_K_M · 20K context
Fastest good-quality model Phi-4 Mini 3.8B ~83 tok/s · Q4_K_M · 28K context
? MMLU (Massive Multitask Language Understanding) measures general knowledge across 57 subjects. Higher = more capable. Sorted best-first.

Runs well 22

  • Qwen3.5 9B 9B Great VisionTool useReasoning
    MMLU 82.5
    Q4_K_M
    Context 22K Speed ~46 tok/s
    Q8_0 Doesn't fit · needs 8.9 GB
  • Qwen3.5 4B 4B Great VisionTool useReasoning
    MMLU 79.1
    Q4_K_M
    Context 111K Speed ~81 tok/s
    Q8_0
    Context 59K Speed ~56 tok/s
  • Qwen 2.5 7B 7.62B Good Tool use
    MMLU 74.2
    Q4_K_M
    Context 24K Speed ~51 tok/s
    Q8_0 Doesn't fit · needs 8.2 GB

Runs well 22

  • Qwen3.5 9B 9B Great VisionTool useReasoning
    MMLU 82.5
    Q4_K_M
    Context 22K Speed ~46 tok/s
    Q8_0 Doesn't fit · needs 8.9 GB
  • Qwen3.5 4B 4B Great VisionTool useReasoning
    MMLU 79.1
    Q4_K_M
    Context 111K Speed ~81 tok/s
    Q8_0
    Context 59K Speed ~56 tok/s
  • Qwen 2.5 7B 7.62B Good Tool use
    MMLU 74.2
    Q4_K_M
    Context 24K Speed ~51 tok/s
    Q8_0 Doesn't fit · needs 8.2 GB
  • Qwen 2.5 VL 7B 7.62B Good VisionTool use
    MMLU 74.2
    Q4_K_M
    Context 24K Speed ~51 tok/s
    Q8_0 Doesn't fit · needs 8.2 GB
  • Phi-4 Mini 3.8B 3.84B Good
    MMLU 70
    Q4_K_M
    Context 28K Speed ~83 tok/s
    Q8_0 Tight fit · 15K context
  • Gemma 4 E4B 4.5B Good VisionTool useReasoning
    MMLU 69.4
    Q4_K_M
    Context 64K Speed ~48 tok/s
    Q8_0 Doesn't fit · needs 7.5 GB
  • Qwen 2.5 Coder 7B 7.62B Good
    MMLU 68
    Q4_K_M
    Context 24K Speed ~51 tok/s
    Q8_0 Doesn't fit · needs 8.2 GB
  • Qwen 2.5 VL 3B 3.09B Fair Vision
    MMLU 65.6
    Q4_K_M
    Context 119K Speed ~98 tok/s
    Q8_0
    Context 79K Speed ~67 tok/s
  • Qwen 2.5 3B 3.09B Fair Tool use
    MMLU 65.6
    Q4_K_M
    Context 32K Speed ~98 tok/s
    Q8_0
    Context 32K Speed ~67 tok/s
  • SmallThinker 3B 3.09B Fair Reasoning
    MMLU 65
    Q4_K_M
    Context 32K Speed ~98 tok/s
    Q8_0
    Context 32K Speed ~67 tok/s
  • Llama 3.2 3B 3.21B Fair Tool use
    MMLU 63.4
    Q4_K_M
    Context 37K Speed ~95 tok/s
    Q8_0
    Context 24K Speed ~65 tok/s
    fp16 Doesn't fit · needs 6.5 GB
  • Gemma 3 4B 3.88B Fair Vision
    MMLU 63
    Q4_K_M
    Context 128K Speed ~83 tok/s
    Q8_0
    Context 98K Speed ~56 tok/s
  • Gemma 4 E2B 2.3B Fair VisionTool useReasoning
    MMLU 60
    Q4_K_M
    Context 128K Speed ~68 tok/s
    Q8_0
    Context 128K Speed ~51 tok/s
  • DeepSeek R1 Distill Qwen 7B 7.62B Fair Reasoning
    MMLU 58
    Q4_K_M
    Context 24K Speed ~51 tok/s
    Q8_0 Doesn't fit · needs 8.2 GB
  • Qwen3.5 2B 2B Fair VisionTool useReasoning
    MMLU 55.3
    Q4_K_M
    Context 256K Speed ~132 tok/s
    Q8_0
    Context 256K Speed ~100 tok/s
  • Llama 3.2 1B 1.24B Basic Tool use
    MMLU 49.3
    Q4_K_M
    Context 128K Speed ~159 tok/s
    Q8_0
    Context 128K Speed ~124 tok/s
  • Qwen3.5 0.8B 0.8B Basic VisionTool useReasoning
    MMLU 29.7
    Q4_K_M
    Context 256K Speed ~192 tok/s
    Q8_0
    Context 256K Speed ~164 tok/s
  • Nemotron 3 Nano 4B 3.97B Basic ReasoningTool use
    MMLU
    Q4_K_M
    Context 215K Speed ~76 tok/s
    Q8_0
    Context 137K Speed ~58 tok/s
  • LFM2.5 2.6B 2.7B Basic Tool use
    MMLU
    Q4_K_M
    Context 128K Speed ~113 tok/s
    Q8_0
    Context 128K Speed ~78 tok/s
  • Ornith 1.5 9B 9.65B Basic Tool useReasoning
    MMLU
    Q4_K_M
    Context 20K Speed ~45 tok/s
    Q8_0 Doesn't fit · needs 9.1 GB
  • MiMo V2.6 Distill Qwen 9B 9.41B Basic VisionTool useReasoning
    MMLU
    Q4_K_M
    Context 18K Speed ~45 tok/s
    Q8_0 Doesn't fit · needs 8.9 GB
  • Nemotron 3.5 Bolt E4B 8B Basic Tool useReasoning
    MMLU
    Q4_K_M
    Context 16K Speed ~43 tok/s
    Q8_0 Doesn't fit · needs 7.5 GB

Tight fit 6

  • Qwen3 8B 8.2B Great ReasoningTool use
    MMLU 79
    Q4_K_M
    Context 7K Speed ~48 tok/s

    Only 7K context — under the 16K needed to be practical

    Q8_0 Doesn't fit · needs 8.8 GB
    GPUs that can run this

    As an Amazon Associate, I earn from qualifying purchases.

  • Phi-3 Mini 3.8B 3.82B Good
    MMLU 70.9
    Q4_K_M
    Context 9K Speed ~85 tok/s

    Only 9K context — under the 16K needed to be practical

    Q8_0
    Context 5K Speed ~57 tok/s

    Only 5K context — under the 16K needed to be practical

    GPUs that can run this

    As an Amazon Associate, I earn from qualifying purchases.

  • Llama 3.1 8B 8.03B Good Tool use
    MMLU 69.4
    Q4_K_M
    Context 8K Speed ~49 tok/s

    Only 8K context — under the 16K needed to be practical

    Q8_0 Doesn't fit · needs 8.7 GB
    fp16 Doesn't fit · needs 16.2 GB
    GPUs that can run this

    As an Amazon Associate, I earn from qualifying purchases.

Tight fit 6

Notify me when new models fit my GPU

An email when a new model fits your RTX A2000 — no spam, unsubscribe anytime.

Doesn't fit 72

  • DeepSeek R1 0528 671B Excellent Reasoning
    MMLU 90.8
    Q4_K_M Needs 409.3 GB — 403.3 GB over
    Q8_0 Needs 713.4 GB — 707.4 GB over
  • Qwen3 Next 80B-A3B 80B Excellent Tool use
    MMLU 90
    Q4_K_M Needs 48.4 GB — 42.4 GB over
    Q8_0 Needs 84.8 GB — 78.8 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 — 624.1 GB over
    Q8_0 Needs 1090.1 GB — 1084.1 GB over

Doesn't fit 72