DeepSeek-V4-Flash-GGUF
No other sizes can be provided unfortunately as MXFP4 does not quantize properly.
Params
—
Context
—
Downloads 30d
245 K
Likes
33
Download history
daily snapshots · 10 days245 K245 K
Jul 28Jul 31Aug 3Aug 6
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| DeepSeek-V4-Flash-MXFP4-00002-of-00004.gguf | GGUF | 39.6 GB | 44.1 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ ollama run deepseek-v4-flash-gguf # pin the quantization explicitly $ ollama run deepseek-v4-flash-gguf-gguf
$ huggingface-cli download bartowski/DeepSeek-V4-Flash-GGUF-GGUF \
DeepSeek-V4-Flash-MXFP4-00002-of-00004.gguf --local-dir .
$ llama-cli -m DeepSeek-V4-Flash-MXFP4-00002-of-00004.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/deepseek-v4-flash-gguf
{
"hf_id": "bartowski/DeepSeek-V4-Flash-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "mit", "commercial": "yes" },
"downloads_30d": 244987,
"vram_estimates": [
{ "quant": "GGUF", "gb": 44.1 }
],
"updated_at": "2026-07-28T18:07:23Z"
}
Specifications
- Licence
- mit
- First seen on the Hub
- 2026-06-29
- Base model
- DeepSeek-V4-Flash
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.