Can I Run MiMo-V2.5 310B on NVIDIA DGX Spark?
Written by Jakub Rusinowski · Last updated September 6, 2026
Not at Q4_K_M — that needs 191.9 GB at 8K context and the NVIDIA DGX Spark has 128 GB. Drop to Q2_K and it fits in 106.6 GB, with up to 32K of context.
Get a personalized upgrade path →
The numbers
| Model | MiMo-V2.5 310B |
| Parameters | 310B/15B active |
| Quantization | Q4_K_M |
| VRAM needed (8K context) | 191.9 GB |
| NVIDIA DGX Spark VRAM | 128 GB |
| Verdict | Runs at a lower quant |
| Fits at | Q2_K (106.6 GB) |
| Max context | 32K |
MiMo-V2.5 310B on the NVIDIA DGX Spark: VRAM by quantization
| Quant | VRAM needed | Fits 128 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 624.7 GB | ✗ No | — | — |
| Q8_0 | 334.1 GB | ✗ No | — | — |
| Q6_K | 258.9 GB | ✗ No | — | — |
| Q5_K_M | 224.4 GB | ✗ No | — | — |
| Q4_K_M | 191.9 GB | ✗ No | — | — |
| Q3_K_M | 136.8 GB | ✗ No | — | — |
| Q2_K | 106.6 GB | ✓ Yes | 32K | — |
Assumes an 8K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 128 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA DGX Spark: 8K 191.9 GB ✗ · 32K 203.5 GB ✗ · 128K 250.2 GB ✗. Past 8K it no longer fits 128 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
What to do next
Quantize to Q2_K. That is the cheapest fix — it costs some quality but no money.
No compatible GPU? MiMo-V2.5 310B on 192 GB of system RAM, CPU only: runs.
Running MiMo-V2.5 310B on this card:
MiMo-V2.5 310B needs ~192 GB but this GPU has 128 GB. Rent a 8× H100 (640 GB)-class GPU by the hour instead of buying one:
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Other MiMo-V2.5 sizes on the NVIDIA DGX Spark
- MiMo-V2.5-Pro 1T — does not fit (610.3 GB)
MiMo-V2.5 310B on nearby hardware
- NVIDIA RTX PRO 6000 Blackwell (96 GB) — does not fit
- Apple M2 Ultra (192 GB) — runs at a lower quant
All MiMo-V2.5 sizes on the NVIDIA DGX Spark | MiMo-V2.5 310B model page | NVIDIA DGX Spark GPU page | VRAM calculator | Check your hardware