What can it run
Popular open-weight models, and the cheapest box we track that has room for each one. Memory capacity decides whether a model loads at all, so this is the first question worth answering.
The requirement is the weights at that quantization plus a 20 percent allowance for the KV cache, activations, and the runtime. It is arithmetic on the format, not a measurement. Long contexts and large batches push the real number up, sometimes a lot. Every parameter count links to the model card it came from.
Search
Family
Quantization
Hardware budget
9 of 9 models
Qwen3-8B
8.2B parameters
Model card: "Number of Parameters: 8.2B". Context 32,768 natively, 131,072 with YaRN.
| Quantization ? | Needs | Cheapest that fits | Options |
|---|---|---|---|
| Q4 (4-bit) | 4.9 GB | AMD Radeon RX 7900 XTX ($930) | 15 |
Parameter count from Qwen3-8B model card
gpt-oss-20b
21B parameters · 3.6B active per token
OpenAI: "21B parameters with 3.6B active parameters"; card says it can run within 16GB of memory.
| Quantization ? | Needs | Cheapest that fits | Options |
|---|---|---|---|
| Q4 (4-bit) | 12.6 GB | AMD Radeon RX 7900 XTX ($930) | 15 |
Parameter count from gpt-oss-120b model card
Mistral Small 3.2 24B
24B parameters
Model card lists 24B params. Mistral does not state a context window on the card.
| Quantization ? | Needs | Cheapest that fits | Options |
|---|---|---|---|
| Q4 (4-bit) | 14.4 GB | AMD Radeon RX 7900 XTX ($930) | 15 |
Parameter count from Mistral Small 3.2 24B Instruct model card
Gemma 3 27B
27B parameters
Model card lists 27B params, with a 128K input context window.
| Quantization ? | Needs | Cheapest that fits | Options |
|---|---|---|---|
| Q4 (4-bit) | 16.2 GB | AMD Radeon RX 7900 XTX ($930) | 15 |
Parameter count from Gemma 3 27B IT model card
Llama 3.3 70B Instruct
70B parameters
Card table lists 70B; the computed safetensors count reads 71B. We use the nominal 70B.
| Quantization ? | Needs | Cheapest that fits | Options |
|---|---|---|---|
| Q4 (4-bit) | 42.0 GB | NVIDIA Jetson AGX Orin 64GB Developer Kit ($3,249) | 11 |
Parameter count from Llama-3.3-70B-Instruct model card
gpt-oss-120b
117B parameters · 5.1B active per token
OpenAI: "117B parameters with 5.1B active parameters"; designed to fit a single 80GB GPU using MXFP4.
| Quantization ? | Needs | Cheapest that fits | Options |
|---|---|---|---|
| Q4 (4-bit) | 70.2 GB | GMKtec EVO-X2 (Ryzen AI Max+ 395, 128GB) ($3,500) | 8 |
Parameter count from gpt-oss-120b model card
Qwen3-235B-A22B
235B parameters · 22B active per token
Mixture of experts: "235B in total and 22B activated". All weights must still be resident.
| Quantization ? | Needs | Cheapest that fits | Options |
|---|---|---|---|
| Q4 (4-bit) | 141.0 GB | Apple Mac Studio (M3 Ultra, 512GB) (price unconfirmed) | 1 |
Parameter count from Qwen3-235B-A22B model card
DeepSeek-V3
671B parameters · 37B active per token
"671B total parameters" with "37B activated for each token". The HF upload totals 685B including the MTP module.
| Quantization ? | Needs | Cheapest that fits | Options |
|---|---|---|---|
| Q4 (4-bit) | 402.6 GB | Apple Mac Studio (M3 Ultra, 512GB) (price unconfirmed) | 1 |
Parameter count from DeepSeek-V3 model card
Kimi K3
2800B parameters · 104B active per token
Mixture of experts: card table reads Total Parameters 2.8T, Activated Parameters 104B, 896 experts with 16 selected per token, 1,048,576 context. All weights must be resident, so nothing we track fits it at any quantization.
| Quantization ? | Needs | Cheapest that fits | Options |
|---|---|---|---|
| Q4 (4-bit) | 1680.0 GB | Nothing we track fits it | 0 |
Parameter count from Kimi-K3 model card
Mixture-of-experts models activate only a fraction of their weights per token, but every weight still has to be resident in memory, so sizing uses the total. See what can you actually run at home for why capacity and bandwidth answer different questions, and our methodology for how these figures are sourced.