What Models?

Pick the right model for your GPU — in seconds.

What AI models can a T400 (2 GB) run?

The T400 has 2 GB of VRAM and 80 GB/s memory bandwidth. 4 models run well on it and 3 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 2B Q4_K_M 73K context · ~37 tok/s · MMLU 55.3
  2. Llama 3.2 1B Q8_0 21K context · ~34 tok/s · MMLU 49.3
  3. Qwen3.5 0.8B Q8_0 112K context · ~45 tok/s · MMLU 29.7

Best for coding

Highest SWE-bench Verified score among models that run well

No benchmarked models run well on this configuration.

Upgrade options

The cheapest GPUs with more VRAM than the T400, by launch MSRP.

As an Amazon Associate, I earn from qualifying purchases.

Every model on the T400

10 of 200 model configurations can run on 2 GB — sorted by quality

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

Largest that runs well LFM2.5 2.6B 2.7B params · Q4_K_M · 29K context
? MMLU (Massive Multitask Language Understanding) measures general knowledge across 57 subjects. Higher = more capable. Sorted best-first.

Runs well 4

  • Qwen3.5 2B 2B Fair VisionTool useReasoning
    MMLU 55.3
    Q4_K_M
    Context 73K Speed ~37 tok/s
    Q8_0 Tight fit · 11K context
  • Llama 3.2 1B 1.24B Basic Tool use
    MMLU 49.3
    Q4_K_M
    Context 38K Speed ~44 tok/s
    Q8_0
    Context 21K Speed ~34 tok/s
  • Qwen3.5 0.8B 0.8B Basic VisionTool useReasoning
    MMLU 29.7
    Q4_K_M
    Context 136K Speed ~53 tok/s
    Q8_0
    Context 112K Speed ~45 tok/s

Runs well 4

  • Qwen3.5 2B 2B Fair VisionTool useReasoning
    MMLU 55.3
    Q4_K_M
    Context 73K Speed ~37 tok/s
    Q8_0 Tight fit · 11K context
  • Llama 3.2 1B 1.24B Basic Tool use
    MMLU 49.3
    Q4_K_M
    Context 38K Speed ~44 tok/s
    Q8_0
    Context 21K Speed ~34 tok/s
  • Qwen3.5 0.8B 0.8B Basic VisionTool useReasoning
    MMLU 29.7
    Q4_K_M
    Context 136K Speed ~53 tok/s
    Q8_0
    Context 112K Speed ~45 tok/s
  • LFM2.5 2.6B 2.7B Basic Tool use
    MMLU
    Q4_K_M
    Context 29K Speed ~31 tok/s
    Q8_0 Doesn't fit · needs 2.7 GB

Tight fit 3

Notify me when new models fit my GPU

An email when a new model fits your T400 — no spam, unsubscribe anytime.

Doesn't fit 93

  • DeepSeek R1 0528 671B Excellent Reasoning
    MMLU 90.8
    Q4_K_M Needs 409.3 GB — 407.3 GB over
    Q8_0 Needs 713.4 GB — 711.4 GB over
  • Qwen3 Next 80B-A3B 80B Excellent Tool use
    MMLU 90
    Q4_K_M Needs 48.4 GB — 46.4 GB over
    Q8_0 Needs 84.8 GB — 82.8 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 — 628.1 GB over
    Q8_0 Needs 1090.1 GB — 1088.1 GB over

Doesn't fit 93