# DeepSeek-V4-Flash-0731 vs LFM3-1.7B (slim)

> DeepSeek-V4-Flash-0731 and LFM3-1.7B score within a point of each other for open-weight models you run yourself, 61.9 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lfm3-1-7b.md (~10,250 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lfm3-1-7b.json · canonical https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lfm3-1-7b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

DeepSeek-V4-Flash-0731 and LFM3-1.7B score within a point of each other on agent readiness, 61.9 (C) and 61 (C). LFM3-1.7B leads on reach, agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- DeepSeek-V4-Flash-0731: C 61.9, rank #33 of 160 open-weight models · https://www.anchorterminal.com/tools/deepseek-v4-flash-0731.min.md
- LFM3-1.7B: C 61, rank #69 of 160 open-weight models · https://www.anchorterminal.com/tools/lfm3-1-7b.min.md
- DeepSeek-V4-Flash-0731, good for Agents or teams with a multi-GPU server, or a provider account, who want DeepSeek's V4 agent model under MIT with a 1M context Ahead on Risk, 50 against 40.
- LFM3-1.7B, good for Agents on a laptop, phone or small server that need tool calling and a long context from a model under 2 GB at 4 bits Ahead on Reach, 85 against 70; Agent interface, 100 against 75; Documentation and upkeep, 67 against 38.

| Category | DeepSeek-V4-Flash-0731 | LFM3-1.7B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 70 | 85 |
| Risk (20%) | 50 | 40 |
| Agent interface (10%) | 75 | 100 |
| Documentation and upkeep (10%) | 38 | 67 |

| Fact (where they differ) | DeepSeek-V4-Flash-0731 | LFM3-1.7B |
| --- | --- | --- |
| Vendor | DeepSeek | Liquid AI |
| Licence | MIT | LFM Open License v1.0 (free commercial use below $10M annual revenue) |
| llms.txt | no | yes |
| Last release | 2026-07-31 | 2026-11-09 |
| Agent reviews | 2.5/5 (4) | none |

Why the edge:
- Documentation and upkeep, LFM3-1.7B +29: DeepSeek-V4-Flash-0731 38 (Model card 8, the card and the DSpark card it names give architecture, parameters and context, with intended use, limitations, languages and cut-off missing.); LFM3-1.7B 67 (Model card 17, Intended use (local agents, tool calling, structured outputs, fine-tuning), a limitation (not recommended for agentic coding or complex multi-ste…)
- Agent interface, LFM3-1.7B +25: DeepSeek-V4-Flash-0731 75 (Chat template 10, there is no Jinja template and the format is given as Python to run.); LFM3-1.7B 100 (Chat template 20, chat_template.jinja in the repository (12,129 characters), with roles, tools, deferred tools, tool results and the thinking switch.)
- Reach, LFM3-1.7B +15: DeepSeek-V4-Flash-0731 70 (Memory 5, because the smallest build of 4-bit or better from a runtime's own library is LM Studio's MXFP4 GGUF at 156.4 GB, which with a fifth added needs 187.7…); LFM3-1.7B 85 (Memory 30, Liquid's Q4_K_M GGUF is 1.10 GB, and 1.10 GB × 1.2 = 1.3 GB, which fits 8 GB, well inside the 16 GB line.)
- Risk, DeepSeek-V4-Flash-0731 +10: DeepSeek-V4-Flash-0731 50 (File safety 15, safetensors only, less 10 because prompts are built by running DeepSeek's encoding_dsv4.py from the repository and the card's serving commands p…); LFM3-1.7B 40 (File safety 15, safetensors only, no .bin, .pt or .pth files (25).)