What Models?

Pick the right model for your GPU — in seconds.

What AI models can a T600 (4 GB) run?

The T600 has 4 GB of VRAM and 160 GB/s memory bandwidth. 12 models run well on it and 2 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 4B Q4_K_M 46K context · ~45 tok/s · MMLU 79.1
  2. Qwen 2.5 3B Q8_0 20K context · ~37 tok/s · MMLU 65.6
  3. Qwen 2.5 VL 3B Q8_0 20K context · ~37 tok/s · MMLU 65.6

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 T600, by launch MSRP.

As an Amazon Associate, I earn from qualifying purchases.

Every model on the T600

23 of 200 model configurations can run on 4 GB — sorted by quality

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

Largest that runs well Qwen3.5 4B 4B params · Q4_K_M · 46K context
Fastest good-quality model Qwen3.5 4B ~45 tok/s · Q4_K_M · 46K context
? MMLU (Massive Multitask Language Understanding) measures general knowledge across 57 subjects. Higher = more capable. Sorted best-first.

Runs well 12

  • Qwen3.5 4B 4B Great VisionTool useReasoning
    MMLU 79.1
    Q4_K_M
    Context 46K Speed ~45 tok/s
    Q8_0 Doesn't fit · needs 4.2 GB
  • Qwen 2.5 VL 3B 3.09B Fair Vision
    MMLU 65.6
    Q4_K_M
    Context 60K Speed ~55 tok/s
    Q8_0
    Context 20K Speed ~37 tok/s
  • Qwen 2.5 3B 3.09B Fair Tool use
    MMLU 65.6
    Q4_K_M
    Context 32K Speed ~55 tok/s
    Q8_0
    Context 20K Speed ~37 tok/s

Runs well 12

  • Qwen3.5 4B 4B Great VisionTool useReasoning
    MMLU 79.1
    Q4_K_M
    Context 46K Speed ~45 tok/s
    Q8_0 Doesn't fit · needs 4.2 GB
  • Qwen 2.5 VL 3B 3.09B Fair Vision
    MMLU 65.6
    Q4_K_M
    Context 60K Speed ~55 tok/s
    Q8_0
    Context 20K Speed ~37 tok/s
  • Qwen 2.5 3B 3.09B Fair Tool use
    MMLU 65.6
    Q4_K_M
    Context 32K Speed ~55 tok/s
    Q8_0
    Context 20K Speed ~37 tok/s
  • SmallThinker 3B 3.09B Fair Reasoning
    MMLU 65
    Q4_K_M
    Context 32K Speed ~55 tok/s
    Q8_0
    Context 20K Speed ~37 tok/s
  • Llama 3.2 3B 3.21B Fair Tool use
    MMLU 63.4
    Q4_K_M
    Context 18K Speed ~53 tok/s
    Q8_0 Tight fit · 5K context
    fp16 Doesn't fit · needs 6.5 GB
  • Gemma 3 4B 3.88B Fair Vision
    MMLU 63
    Q4_K_M
    Context 79K Speed ~46 tok/s
    Q8_0 Doesn't fit · needs 4.1 GB
  • Gemma 4 E2B 2.3B Fair VisionTool useReasoning
    MMLU 60
    Q4_K_M
    Context 128K Speed ~38 tok/s
    Q8_0 Doesn't fit · needs 4.6 GB
  • Qwen3.5 2B 2B Fair VisionTool useReasoning
    MMLU 55.3
    Q4_K_M
    Context 255K Speed ~73 tok/s
    Q8_0
    Context 193K Speed ~56 tok/s
  • Llama 3.2 1B 1.24B Basic Tool use
    MMLU 49.3
    Q4_K_M
    Context 102K Speed ~88 tok/s
    Q8_0
    Context 86K Speed ~69 tok/s
  • Qwen3.5 0.8B 0.8B Basic VisionTool useReasoning
    MMLU 29.7
    Q4_K_M
    Context 256K Speed ~107 tok/s
    Q8_0
    Context 256K Speed ~91 tok/s
  • LFM2.5 2.6B 2.7B Basic Tool use
    MMLU
    Q4_K_M
    Context 128K Speed ~63 tok/s
    Q8_0
    Context 87K Speed ~43 tok/s
  • Nemotron 3 Nano 4B 3.97B Basic ReasoningTool use
    MMLU
    Q4_K_M
    Context 82K Speed ~42 tok/s
    Q8_0 Tight fit · 4K context

Tight fit 2

Notify me when new models fit my GPU

An email when a new model fits your T600 — no spam, unsubscribe anytime.

Doesn't fit 86

  • DeepSeek R1 0528 671B Excellent Reasoning
    MMLU 90.8
    Q4_K_M Needs 409.3 GB — 405.3 GB over
    Q8_0 Needs 713.4 GB — 709.4 GB over
  • Qwen3 Next 80B-A3B 80B Excellent Tool use
    MMLU 90
    Q4_K_M Needs 48.4 GB — 44.4 GB over
    Q8_0 Needs 84.8 GB — 80.8 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 — 626.1 GB over
    Q8_0 Needs 1090.1 GB — 1086.1 GB over

Doesn't fit 86