Best local AI models for AMD R7 M440
4 GB DDR3. At a 4k context, 81 of the 233 models in our catalog with verified parameter counts fit fully, up to Lumina-Next / Lumina-Image 2.0 at 5B parameters.
Check your own machine against every model →The largest models that fit fully
The 30 largest of the 81 models that fit; every smaller model in the catalog fits too. Best quant means the highest quality compression whose weights and 4k context both sit inside the memory.
| Model | Parameters | Best quant that fits | Memory used at 4k |
|---|---|---|---|
| Lumina-Next / Lumina-Image 2.0 | 5B | Q4_K_M | 3.7 GB |
| CogVideoX 2B / 5B | 5B | Q4_K_M | 3.7 GB |
| DeepSeek-VL2 | 4.5B | Q5_K_M | 3.8 GB |
| DeepFloyd IF | 4.3B | Q5_K_M | 3.7 GB |
| Phi-3.5-vision | 4.2B | Q5_K_M | 3.6 GB |
| Qwen3 4B | 4B | Q6_K | 3.9 GB |
| Gemma 3 4B | 4B | Q6_K | 3.9 GB |
| Gemma 4 E4B | 4B | Q6_K | 3.9 GB |
| MiniCPM 3 4B | 4B | Q6_K | 3.9 GB |
| Danube 3 4B | 4B | Q6_K | 3.9 GB |
| Fish Speech 1.5 / OpenAudio S1 | 4B | Q6_K | 3.9 GB |
| Phi-4-mini-instruct | 3.8B | Q6_K | 3.7 GB |
| Phi-3.5 Mini | 3.8B | Q6_K | 3.7 GB |
| OmniGen / OmniGen2 | 3.8B | Q6_K | 3.7 GB |
| SD Cascade (Würstchen v3) | 3.6B | Q6_K | 3.5 GB |
| SDXL Turbo | 3.5B | Q6_K | 3.4 GB |
| SDXL Lightning | 3.5B | Q6_K | 3.4 GB |
| ACE-Step | 3.5B | Q6_K | 3.4 GB |
| MusicGen small/medium/large | 3.3B | Q6_K | 3.2 GB |
| SmolLM3 3B | 3B | Q8_0 | 3.8 GB |
| Replit Code v1.5 3B | 3B | Q8_0 | 3.8 GB |
| Kandinsky 3.1 | 3B | Q8_0 | 3.8 GB |
| Voxtral Mini / Small | 3B | Q8_0 | 3.8 GB |
| Orpheus TTS | 3B | Q8_0 | 3.8 GB |
| Higgs Audio v2 | 3B | Q8_0 | 3.8 GB |
| Allegro | 2.8B | Q8_0 | 3.6 GB |
| Open-Sora Plan | 2.7B | Q8_0 | 3.4 GB |
| LFM2 1.2B / 2.6B | 2.6B | Q8_0 | 3.3 GB |
| Playground v2.5 | 2.6B | Q8_0 | 3.3 GB |
| Stable Diffusion 3.5 Medium | 2.5B | Q8_0 | 3.2 GB |
Close, but only with CPU offload
These need more than the card holds at their smallest practical quant, so part of the model runs from system memory (figures assume 32 GB of it). They work, several times slower.
| Model | Parameters | Memory at FP8 / optimized | System RAM at 4k |
|---|---|---|---|
| Stable Diffusion XL | 3.417B | 4.1 GB needed | 6.1 GB |
| Phi-3 Mini | 3.8B | 4.4 GB needed | 6.4 GB |
| Phi-4-multimodal | 5.6B | 4.1 GB needed | 6.1 GB |
| Magicoder-S-DS 6.7B | 6.7B | 4.9 GB needed | 6.9 GB |
| Mistral 7B | 7B | 5.7 GB needed | 7.7 GB |
| Qwen2.5 0.5B / 1.5B / 3B / 7B | 7B | 5.1 GB needed | 7.1 GB |
| OLMo 2 1B / 7B | 7B | 5.1 GB needed | 7.1 GB |
| Falcon 3 1B / 3B / 7B | 7B | 5.1 GB needed | 7.1 GB |
| Command R7B | 7B | 5.1 GB needed | 7.1 GB |
| OpenHermes 2.5 | 7B | 5.1 GB needed | 7.1 GB |
How to read this
The AMD Radeon R7 M440 is an entry level laptop graphics card equipped with 4 GB of DDR3 video memory. This dedicated memory size is the primary constraint when running artificial intelligence models locally. To execute a model entirely on the graphics hardware, the model files and the active working memory must fit within this 4 GB limit. If a model exceeds this boundary, the execution will fail or slow down significantly.
Quantization is a compression method that reduces the size of neural networks. The quant column indicates the best precision level that fits inside your video memory. For example, smaller models can run at higher quality levels like Q8_0 or Q6_K. Larger models must use tighter compression levels like Q5_K_M or Q4_K_M to stay under the 4 GB limit. Using these specific quants allows you to run capable models without running out of memory.
Several high quality models can fit completely within the graphics memory of the AMD R7 M440. For image generation, Lumina-Next or Lumina-Image 2.0 at 5B fits using the Q4_K_M quant with 3.7 GB used. CogVideoX 2B or 5B fits at 5B using Q4_K_M with 3.7 GB used. For vision and text tasks, DeepSeek-VL2 at 4.5B fits using Q5_K_M with 3.8 GB used, while Phi-3.5-vision at 4.2B fits using Q5_K_M with 3.6 GB used.
Other models fit well within the 4 GB limit. Qwen3 4B, Gemma 3 4B, Gemma 4 E4B, MiniCPM 3 4B, Danube 3 4B, and Fish Speech 1.5 or OpenAudio S1 at 4B all fit using the Q6_K quant with 3.9 GB used. Phi-4-mini-instruct, Phi-3.5 Mini, and OmniGen or OmniGen2 at 3.8B fit using Q6_K with 3.7 GB used. For audio, MusicGen small or medium or large at 3.3B fits using Q6_K with 3.2 GB used. SmolLM3 3B and Orpheus TTS at 3B fit using Q8_0 with 3.8 GB used.
When a model is too large for the 4 GB video memory, you can offload parts of it to your system RAM. This process requires a system with 32 GB of system RAM. For example, Mistral 7B needs 5.7 GB at Q4_K_M and requires 7.7 GB of system RAM. Qwen2.5 0.5B or 1.5B or 3B or 7B at 7B needs 5.1 GB at Q4_K_M and requires 7.1 GB of system RAM. Offloading allows you to run these larger models, but it costs performance because system RAM is much slower than video memory.
Other offload options include Stable Diffusion XL at 3.417B, which needs 4.1 GB at FP8 or optimized and requires 6.1 GB of system RAM. Phi-3 Mini at 3.8B needs 4.4 GB at Q4_K_M and requires 6.4 GB of system RAM. Phi-4-multimodal at 5.6B needs 4.1 GB at Q4_K_M and requires 6.1 GB of system RAM. Magicoder-S-DS 6.7B needs 4.9 GB at Q4_K_M and requires 6.9 GB of system RAM.
You must consider the context window when planning your memory usage. The memory figures listed are calculated using a standard 4k context window. If you increase the context length to process longer documents or chat histories, the memory usage will grow. This extra memory demand can push a model over the 4 GB limit and force slow system RAM usage.