ToolSite MiMo V2.6 Flash VRAM requirements
MiMo V2.6 Flash has 310.8B parameters, of which about 15B are used per token; all 256 experts still have to be in memory. With an 8K-token context and one request it needs about 193 GB of GPU memory at Q4_K_M, 319 GB at FP8 and 637 GB at FP16/BF16. The published weights take 161 GB (4.5 bits/weight). No single GPU in the table holds it at Q4_K_M; it needs a multi-GPU setup.
Open MiMo V2.6 Flash in the calculator
VRAM by quantization
Weights plus the KV cache for 8,192 tokens in FP16 and the runtime overhead (0.5 GB plus 10%). Each row opens the calculator with that setting. What the GGUF names mean.
| Precision | Weights | Total | Smallest setup |
|---|---|---|---|
| As published (4.5 bits/weight) | 161 GB | 178 GB | B200 |
| FP16 / BF16 | 579 GB | 637 GB | 4 × B200 |
| FP8 / INT8 | 289 GB | 319 GB | 2 × B200 |
| INT4 (AWQ / GPTQ) | 154 GB | 170 GB | B200 |
| GGUF Q8_0 | 308 GB | 339 GB | 2 × B200 |
| GGUF Q6_K | 237 GB | 262 GB | 2 × H200 |
| GGUF Q5_K_M | 205 GB | 226 GB | 2 × H200 |
| GGUF Q4_K_M | 175 GB | 193 GB | 2 × H200 |
| GGUF Q3_K_M | 141 GB | 156 GB | B200 |
| GGUF Q2_K | 121 GB | 134 GB | H200 |
KV cache at long context
9 of its 48 layers use full attention and 39 keep a sliding window of 128 tokens. Each extra token of context adds 23 KB of FP16 cache per request once the sliding windows are full. How the KV cache works.
| Context | KV cache, FP16 | KV cache, FP8 | Total at Q4_K_M |
|---|---|---|---|
| 4K tokens | 114 MB | 57 MB | 193 GB |
| 32K tokens | 744 MB | 372 MB | 194 GB |
| 128K tokens | 2.84 GB | 1.42 GB | 196 GB |
| 1M tokens | 22.5 GB | 11.3 GB | 218 GB |
Which GPUs can run MiMo V2.6 Flash
With 8,192 tokens of context. Several GPUs means one tensor-parallel group of 2, 4 or 8 cards.
| GPU | Memory | Q4_K_M | FP8 |
|---|---|---|---|
| RTX 3060 | 12 GB | Needs more than 8 | Needs more than 8 |
| RTX 4060 Ti 16GB | 16 GB | Needs more than 8 | Needs more than 8 |
| RTX 3090 / 4090 | 24 GB | Needs more than 8 | Needs more than 8 |
| RTX 5090 | 32 GB | Needs 8 | Needs more than 8 |
| A100 40GB | 40 GB | Needs 8 | Needs more than 8 |
| Mac, 64 GB unified memory about 75% of it is usable by the GPU by default | 48 GB | Needs 8 | Needs 8 |
| L40S / RTX 6000 Ada | 48 GB | Needs 8 | Needs 8 |
| A100 / H100 80GB | 80 GB | Needs 4 | Needs 8 |
| Mac, 128 GB unified memory about 75% of it is usable by the GPU by default | 96 GB | Needs 4 | Needs 4 |
| H200 | 141 GB | Needs 2 | Needs 4 |
| B200 | 180 GB | Needs 2 | Needs 2 |
How fast MiMo V2.6 Flash writes
Tokens per second for one request with 8,192 tokens of context, estimated from memory bandwidth and the parameters read per token. A dash means it does not fit on one card. Try other settings in the speed calculator.
| Hardware | Bandwidth | Q4_K_M | FP8 |
|---|---|---|---|
| RTX 3060 12GB | 360 GB/s | — | — |
| RTX 4090 | 1,008 GB/s | — | — |
| RTX 5090 | 1,792 GB/s | — | — |
| M4 Max Mac (128 GB) | 546 GB/s | — | — |
| M3 Ultra Mac Studio (512 GB) | 819 GB/s | 25–43 | 16–27 |
| H100 SXM | 3,350 GB/s | — | — |
| H200 | 4,800 GB/s | — | — |
Longest context on one GPU
How many tokens of context fit on a single card with one request and an FP16 KV cache. "Full" means the model's whole context window fits.
| GPU | Memory | Q4_K_M | Q8_0 | FP8 |
|---|---|---|---|---|
| RTX 3060 | 12 GB | No | No | No |
| RTX 4060 Ti 16GB | 16 GB | No | No | No |
| RTX 3090 / 4090 | 24 GB | No | No | No |
| RTX 5090 | 32 GB | No | No | No |
| A100 40GB | 40 GB | No | No | No |
| Mac, 64 GB unified memory | 48 GB | No | No | No |
| L40S / RTX 6000 Ada | 48 GB | No | No | No |
| A100 / H100 80GB | 80 GB | No | No | No |
| Mac, 128 GB unified memory | 96 GB | No | No | No |
| H200 | 141 GB | No | No | No |
| B200 | 180 GB | No | No | No |
Model details
- Parameters
- 310.8B (310,756,322,688)
- Experts
- 256 routed experts, all loaded
- Active per token
- 15B
- Layers
- 9 of its 48 layers use full attention and 39 keep a sliding window of 128 tokens
- Attention cache
- 4 KV heads × 192 keys, 128 values
- Sliding-window layers
- 8 KV heads × 192
- Context length
- 1,048,576 tokens
- Published weights
- 161 GB (4.5 bits/weight)
- On Hugging Face
- XiaomiMiMo/MiMo-V2.6-Flash-RL
Other models
- DeepSeek V4 Flash 0731
- Qwen3.6 35B-A3B
- Qwen3.6 27B
- Qwen3.8 27B
- Qwen3.8 Flash Next
- Qwen3.8 2.4T-A95B
- Qwen3.5 9B
- Qwen3.5 122B-A10B
- Qwen3-Coder-Next
- DeepSeek V4.1 Flash
- DeepSeek V4 Flash
- DeepSeek V4 Pro
- DeepSeek V3.2
- GLM-5.3
- GLM-5.3 Flash
- GLM-5.2
- GLM-4.7 Flash
- Gemma 4 31B
- Gemma 4 26B-A4B
- Gemma 4 12B
- Gemma 4 E4B
- Kimi K3
- MiniMax M3
- MiniMax M2.7
- MiMo V2.6 Pro
- Mistral Medium 3.5 128B
- Nemotron 3 Nano 4B
- Nemotron 3 Nano 30B-A3B
- Nemotron 3 Super 120B-A12B
- Xing 4.0 29B-A4B
- Muse Glimmer 30B
- MiniCPM5 2B
- Llama 3.1 8B
- Llama 3.1 70B
- Qwen3 8B
- Qwen3 30B-A3B
- gpt-oss-20b
- gpt-oss-120b
- DeepSeek V3 / R1
Numbers read from the model files on Hugging Face on .