What GPU do you need to run DeepSeek-V4-Flash?
Weights-only fit: a new Framework Desktop ($6,799). No priced GPU card holds DeepSeek-V4-Flash (about 156.6 GB at UD-Q4_K_XL); this system holds it (weights-only fit, context unknown: no KV cache data; 35.4 GB left beyond the file and headroom), at about 28 tok/s estimate. The weights fit 1 of the 157 GPUs and systems we track; with no KV cache data, context is unknown on all of them.
290.94B parameters, 13B active (mixture-of-experts) (Hugging Face, accessed 2026-10-16). UD-Q4_K_XL GGUF: 155.1 GB (source). No context estimate: DeepSeek V4 compressed/indexed attention (compress_ratios, index_topk) has no verified llama.cpp KV formula yet (details).
Model card: 284B total, 13B activated, 1M context. No plain Q4_K_M GGUF found; size is unsloth UD-Q4_K_XL.
Other places to get it
Checked Nov 14, 2026. We list only copies we opened and checked. Check file hashes for copies from other uploaders.
- ModelScope: Lab's own account
Weights-only fits, context unknown. We have no KV cache data for DeepSeek-V4-Flash, so every fit on this page only checks that the UD-Q4_K_XL file and headroom fit. How much context fits beside the weights is unknown, so none of these is a proven fit for any context length.
Single GPUs the weights fit, cheapest first
| Single GPU that fits | VRAM | Speed estimate | Max context estimate | Price |
|---|---|---|---|---|
| Framework Desktop, AMD Ryzen AI Max+ PRO 495 (Strix Halo), 192 GB | 192 GB | ~28 tok/s | Unknown (no KV data) | low $6,799 |
Every device that runs it
Graphics cards, Macs and mini PCs from the wider hardware list behind My rig, smallest usable memory first. Not sure about yours? Check your exact rig.
Show all 4 devices that run it
| Device | Type | Memory | Speed estimate | Max context estimate | Price |
|---|---|---|---|---|---|
| Apple M3 Ultra 256GB | Mac | 256 GB (~192 usable) | ~68 tok/s | Unknown | No price yet |
| Apple M5 Ultra 256GB | Mac | 256 GB (~192 usable) | ~86 tok/s | Unknown | No price yet |
| Framework Desktop, AMD Ryzen AI Max+ PRO 495 (Strix Halo), 192 GB | Mini PC | 192 GB | ~28 tok/s | Unknown | low $6,799 |
| Apple M5 Ultra 512GB | Mac | 512 GB (~384 usable) | ~86 tok/s | Unknown | No price yet |
Multi-GPU: cards that need two or more
| Cards | Total VRAM | Speed estimate | Max context estimate |
|---|---|---|---|
| 4 × NVIDIA RTX A6000 | 192 GB | ~84 tok/s | Unknown |
Speed calculator
estimateEstimate = bandwidth ÷ GB read per token (the model's listed GGUF file: Q4_K_M for most models, otherwise the quant named in the list; scaled by active/total parameters for MoE), scaled by a per-platform efficiency and fixed per-token costs calibrated to 45 measured llama.cpp benchmarks (2025–26). Fit = file size + 1.5 GB headroom ≤ total VRAM (on Macs, the part of unified memory macOS lets the GPU use by default), and room for at least 4K tokens of context with an 8-bit KV cache. For a model with no KV cache data, only the file and headroom are checked, so a fit says nothing about context. Multi-GPU: VRAM adds, speed stays one card's (a layer split runs the cards in turn); max context uses the total. Speed is for short context. Max context = what is left after the file and a 1 GB runtime reserve ÷ KV cache bytes per token, default FP16 and 8-bit (q8_0) cache. How speed works · how context works