Head to head · Open-weight models you run yourself · October 2026 research run
DeepSeek-V3.2 vs North Mini Code 1.0
North Mini Code 1.0 scores 61 (C) on agent readiness against DeepSeek-V3.2's 58.6 (C), and leads in every scored category. Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons
Which one, for what
Best for Teams with an eight-GPU server who want an MIT agent model with broad runtime support, or agents calling it through a hosted provider
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
689.5 GB of FP8 files and no smaller build from DeepSeek or a runtime library, far beyond 107.4 GB
Best for Developers who want a coding agent on their own GPU with a permissive licence
Ahead on
- Reach, 85 against 60
- Risk, 60 against 50
- Agent interface, 85 against 60
Watch for
No limitations, safety results, languages or data description on the card
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Reach North Mini Code 1.0 +25
DeepSeek-V3.2 60
Memory earns nothing, because the only build from DeepSeek or a runtime's library is the 689.5 GB FP8 release, which needs about 827 GB with the fifth added. Runtimes earn the full 25 for released model code in vLLM, SGLang, llama.cpp and Transformers, and for Ollama 0.40.14, whose llama.cpp pin (b11963) carries the deepseek32 architecture with no gate in Ollama's server code, though its library entry stays retired; nothing from LM Studio. Builds earn 10 for the single FP8 precision DeepSeek publishes. Terms earn the full 15 for MIT with nothing added, and download the full 10 since the repository isn't gated. Hosted earns nothing, since DeepSeek's own API moved to V4 on 24 April 2026 and Hugging Face maps only DeepInfra as live for it on 4 November (Novita and Featherless in error), where the line needs two providers. Fireworks' model page says Serverless Not Supported and lists it only for on-demand deployment on dedicated GPUs, which is renting the hardware rather than calling a served model.
North Mini Code 1.0 85
Memory 25, the smallest build from Cohere is the w4a16 repository, 19.38 GB, and 19.38 GB × 1.2 = 23.3 GB, within 24 GB. Unsloth's GGUF isn't read for this line. Runtimes 20, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the cohere2_moe model, and llama.cpp b12242 has the cohere2moe architecture. Builds 15, Quantised builds from Cohere at two precisions, FP8 and 4-bit weights (w4a16), each in its own repository. Terms 15, Apache 2.0 in the metadata and on the card, an OSI licence with nothing added. Download 10, the Hub API reports gated false for the model and its builds on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 25 + 20 + 15 + 15 + 10 + 0 = 85.
Agent interface North Mini Code 1.0 +25
DeepSeek-V3.2 60
The chat template earns 10, as the format exists only as Python code to run. The tool-calling format earns 10 because DeepSeek documents the DSML format in code but names no runtime parser, which only vLLM's own recipe does. Trained tool calling earns the full 20 for several calls in one block. Structured output earns nothing, as JSON output isn't documented. Reasoning control earns 10 for thinking or chat mode per request with reasoning_content returned. Context earns 10 for 128K trained tokens.
North Mini Code 1.0 85
Chat template 20, chat_template.jinja in the repository (12,397 characters). Tool-calling format 25, the card documents how tools are declared (JSON schema through the chat template), how the call and its thinking go back into the history and how results are appended, and names the cohere_command4 tool-call parser for vLLM, which released vLLM has. Trained tool calling 20, the card says the model was specifically trained with tool-use capabilities for agentic coding, with reinforcement learning on verifiable tasks, and the template renders every call in a turn with thinking between them. Structured output 0, JSON schema is for describing tools. Reasoning control 10, the template has a reasoning_effort setting, and the card names the cohere_command4 reasoning parser, which returns thinking apart from the answer. Context 10, 256K tokens per the card, with 64K of output, and 500,000 positions in config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.
Risk North Mini Code 1.0 +10
DeepSeek-V3.2 50
File safety earns 15, safetensors only but 10 off because prompts are built by running DeepSeek's Python from the repository. Provenance earns the full 15 for the deepseek-ai organisation and a SHA-256 on every shard. Safety evaluation earns nothing, since no results are published anywhere. Agent guidance earns nothing, since the notes about the parser and the developer role are usage notes, read alike for all three DeepSeek listings. Licence risk keeps the full 15 for plain MIT. The security programme earns 5 for the security@deepseek.com reporting address on DeepSeek's site, with no public advisories.
North Mini Code 1.0 60
File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in Cohere's verified CohereLabs organisation, which cohere.com links to per our other Cohere listings (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or safety section, and nothing on prompt injection, instruction priority or what the model refuses. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 5, Cohere's trust centre holds a responsible disclosure policy with a bug bounty, as recorded on our Cohere listings (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.
Score by category
| Category | Weight this run | DeepSeek-V3.2 | North Mini Code 1.0 | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 60 | 85 | North Mini Code 1.0 +25 |
| Risk | 20%20 | 50 | 60 | North Mini Code 1.0 +10 |
| Agent interface | 10%10 | 60 | 85 | North Mini Code 1.0 +25 |
| Documentation and upkeep | 10%10 | 34 | 36 | North Mini Code 1.0 +2 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 58.6/100 | C 61/100 |
Facts side by side
| Fact | DeepSeek-V3.2 | North Mini Code 1.0 |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | DeepSeek | Cohere |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2025-12-01 | 2026-07-29 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | 2.3/5 (4) | none |
Verdicts
DeepSeek-V3.2
DeepSeek-V3.2 is an MIT-licensed reasoning model trained for parallel tool calls, with thinking chosen per request, for long agent work. It needs about 690 GB of FP8 files, eight 80 GB GPUs in vLLM's recipe and prompts built from DeepSeek's Python. The main risk is neglect, with no file changes since December 2025 and no safety evaluation.
North Mini Code 1.0
A coding agent model that fits one 24 GB GPU at 4 bits, trained for tool use, with a 256K context, Apache 2.0 and four released runtimes. It's a research release and reads like one: nothing on limitations, safety or data, the card's run instructions are out of date, and Cohere hasn't answered a question on the repository.
Before you call either
DeepSeek-V3.2
- Start it with vLLM's recipe, vllm serve deepseek-ai/DeepSeek-V3.2 --tensor-parallel-size 8 --tokenizer-mode deepseek_v32 --enable-auto-tool-choice --tool-call-parser deepseek_v32 --reasoning-parser deepseek_v3
- It doesn't fit the 107.4 GB reference machine at any qualifying build, so call DeepInfra (deepseek-ai/DeepSeek-V3.2) or deploy it on Fireworks instead
- Outside vLLM, build prompts with encoding/encoding_dsv32.py and wrap parse_message_from_completion_text in error handling, since DeepSeek says it handles well-formed output only
- Pick thinking or chat with thinking_mode, and read the reasoning from reasoning_content
- Send developer messages only for search-agent prompts, the only use DeepSeek gives that role
- Use temperature 1.0 and top_p 0.95 and keep prompts within 128K tokens
North Mini Code 1.0
- Serve it with vLLM 0.33.0 or later and
--tool-call-parser cohere_command4 --reasoning-parser cohere_command4 --enable-auto-tool-choice, withcohere_melodyinstalled - Pass the model's thinking back with its tool calls on every turn. The card says results drop without it
- Describe tools in JSON schema and append tool results as a dictionary with the tool role
- Use temperature 1.0 and top_p 0.95
- For llama.cpp the GGUF files are Unsloth's or bartowski's conversions, not Cohere's
- It's text only. Don't send images
Questions
Which is better for AI agents, DeepSeek-V3.2 or North Mini Code 1.0?
North Mini Code 1.0 scores 61 (C) on agent readiness against DeepSeek-V3.2's 58.6 (C), and leads in every scored category.
Other comparisons with DeepSeek-V3.2 or North Mini Code 1.0
- Agents-A1-4B vs DeepSeek-V3.2
- Agents-A1-4B vs North Mini Code 1.0
- Apertus v1.5 8B vs DeepSeek-V3.2
- Apertus v1.5 8B vs North Mini Code 1.0
- Apodex-1.1-mini vs DeepSeek-V3.2
- Apodex-1.1-mini vs North Mini Code 1.0
- Arete-27B vs DeepSeek-V3.2
- Arete-27B vs North Mini Code 1.0
- BigBang-v1 vs DeepSeek-V3.2
- BigBang-v1 vs North Mini Code 1.0
- Carbon-X vs DeepSeek-V3.2
- Carbon-X vs North Mini Code 1.0
- Cola2 vs DeepSeek-V3.2
- Cola2 vs North Mini Code 1.0
- Cosmos-Reason2-2B vs DeepSeek-V3.2
- Cosmos-Reason2-2B vs North Mini Code 1.0
- Darwin-36B-Opus vs DeepSeek-V3.2
- Darwin-36B-Opus vs North Mini Code 1.0
- DeepSeek-V3.2 vs DeepSeek V4.1 Flash
- DeepSeek-V3.2 vs DeepSeek-V4-Flash-0731
- DeepSeek-V3.2 vs Devstral Small 2
- DeepSeek-V3.2 vs DiffusionGemma 26B A4B IT
- DeepSeek-V3.2 vs EXAONE 4.5 33B
- DeepSeek-V3.2 vs Gemma 4 12B IT
- DeepSeek-V3.2 vs Gemma 4 26B A4B IT
- DeepSeek-V3.2 vs Gemma 4 31B IT
- DeepSeek-V3.2 vs Gemma 4 E2B IT
- DeepSeek-V3.2 vs Gemma 4 E4B IT
- DeepSeek-V3.2 vs GLM-4.5-Air
- DeepSeek-V3.2 vs GLM-4.7-Flash
- DeepSeek-V3.2 vs GLM-5.3
- DeepSeek-V3.2 vs GLM-5.3-Flash
- DeepSeek-V3.2 vs gpt-oss-120b
- DeepSeek-V3.2 vs gpt-oss-20b
- DeepSeek-V3.2 vs Granite 4.2 30B
- DeepSeek-V3.2 vs Granite 4.2 3B
- DeepSeek-V3.2 vs Granite 4.2 8B
- DeepSeek-V3.2 vs Hy-Memory-30B-A3B
- DeepSeek-V3.2 vs Hy3
- DeepSeek-V3.2 vs Inkling
- DeepSeek-V3.2 vs Inkling-Small
- DeepSeek-V3.2 vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- DeepSeek-V3.2 vs Kimi K3
- DeepSeek-V3.2 vs Kimi K3.1 Pro
- DeepSeek-V3.2 vs Kolibri-1
- DeepSeek-V3.2 vs Kronos
- DeepSeek-V3.2 vs Laguna M.1
- DeepSeek-V3.2 vs Laguna S 2.1
- DeepSeek-V3.2 vs Laguna XS 2.1
- DeepSeek-V3.2 vs LBS-27B
- DeepSeek-V3.2 vs LFM2.5-2.6B
- DeepSeek-V3.2 vs LFM3-1.7B
- DeepSeek-V3.2 vs LFM3-Audio-2B
- DeepSeek-V3.2 vs LFM3-Omni-2B
- DeepSeek-V3.2 vs LFM3-VL-2B
- DeepSeek-V3.2 vs Ling-3.0-tiny
- DeepSeek-V3.2 vs Ling-3.1-flash-1019
- DeepSeek-V3.2 vs LongCat-2.5
- DeepSeek-V3.2 vs MiMo-V2.6 Distill Qwen 9B
- DeepSeek-V3.2 vs MiMo-V2.6-Flash-RL
- DeepSeek-V3.2 vs MiniCPM-o 4.5
- DeepSeek-V3.2 vs MiniCPM-V 4.7 1B
- DeepSeek-V3.2 vs MiniCPM-V 4.7 35B-A3B
- DeepSeek-V3.2 vs MiniCPM5-2B
- DeepSeek-V3.2 vs MiniMax-M2.5
- DeepSeek-V3.2 vs MiniMax-M2.7
- DeepSeek-V3.2 vs MiniMax-M3.1-Flash
- DeepSeek-V3.2 vs Mistral Large 4
- DeepSeek-V3.2 vs Muse Glimmer 30B
- DeepSeek-V3.2 vs Nanbeige4.2-3B
- DeepSeek-V3.2 vs Nanbeige4.3-33B
- DeepSeek-V3.2 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- DeepSeek-V3.2 vs Nemotron 3.5 Lightning 30B A3B
- DeepSeek-V3.2 vs Nemotron 3 Nano 30B A3B
- DeepSeek-V3.2 vs Nemotron 3 Nano 4B
- DeepSeek-V3.2 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- DeepSeek-V3.2 vs Nemotron 3 Super 120B A12B
- DeepSeek-V3.2 vs Nemotron 3 Ultra 550B A55B
- DeepSeek-V3.2 vs occamy-1.0
- DeepSeek-V3.2 vs Olmo 3 7B Think
- DeepSeek-V3.2 vs Ornith-1.5-122B
- DeepSeek-V3.2 vs Ornith-1.5-35B-A3B
- DeepSeek-V3.2 vs Ornith-1.5-397B
- DeepSeek-V3.2 vs Ornith-1.5-9B
- DeepSeek-V3.2 vs OTel-2.0-LLM-31B-IT
- DeepSeek-V3.2 vs Qwen-AgentWorld-35B-A3B
- DeepSeek-V3.2 vs Qwen3-30B-A3B-Instruct-2507
- DeepSeek-V3.2 vs Qwen3-4B-Instruct-2507
- DeepSeek-V3.2 vs Qwen3.5-0.8B
- DeepSeek-V3.2 vs Qwen3.5-122B-A10B
- DeepSeek-V3.2 vs Qwen3.5-2B
- DeepSeek-V3.2 vs Qwen3.5-397B-A17B
- DeepSeek-V3.2 vs Qwen3.5-4B
- DeepSeek-V3.2 vs Qwen3.5-9B
- DeepSeek-V3.2 vs Qwen3.6-27B
- DeepSeek-V3.2 vs Qwen3.6-35B-A3B
- DeepSeek-V3.2 vs Qwen3.8-27B
- DeepSeek-V3.2 vs Qwen3.8-Flash-Next
- DeepSeek-V3.2 vs Qwen3-Coder-30B-A3B-Instruct
- DeepSeek-V3.2 vs Qwen3-Coder-Next
- DeepSeek-V3.2 vs Qwen3-Omni-30B-A3B-Instruct
- DeepSeek-V3.2 vs Qwen3-VL-2B-Instruct
- DeepSeek-V3.2 vs Qwen3-VL-30B-A3B-Instruct
- DeepSeek-V3.2 vs Qwen3-VL-32B-Instruct
- DeepSeek-V3.2 vs Qwen3-VL-4B-Instruct
- DeepSeek-V3.2 vs Qwen3-VL-8B-Instruct
- DeepSeek-V3.2 vs Qwopus3.8-27B-Flash-V2
- DeepSeek-V3.2 vs Recursive Flint
- DeepSeek-V3.2 vs Ripple-65B Preview
- DeepSeek-V3.2 vs SenseNova-Loop-9B-Preview
- DeepSeek-V3.2 vs SmolLM3-3B
- DeepSeek-V3.2 vs Spark-X2.6-4B
- DeepSeek-V3.2 vs Step 3.7 Flash
- DeepSeek-V3.2 vs Swift 1.5 Qwen3.8-27B
- DeepSeek-V3.2 vs Swift 1.5 Qwen3.8-Flash-Next
- DeepSeek-V3.2 vs ThinkingCap (Qwen3.8 27B)
- DeepSeek-V3.2 vs Baidu Unlimited-OCR-2
- DeepSeek-V3.2 vs WeVisOne-VL-2B
- DeepSeek-V3.2 vs WeVisOne-VL-4B
- DeepSeek-V3.2 vs ZAYA1-8B
- DeepSeek V4.1 Flash vs North Mini Code 1.0
- DeepSeek-V4-Flash-0731 vs North Mini Code 1.0
- Devstral Small 2 vs North Mini Code 1.0
- DiffusionGemma 26B A4B IT vs North Mini Code 1.0
- EXAONE 4.5 33B vs North Mini Code 1.0
- Gemma 4 12B IT vs North Mini Code 1.0
- Gemma 4 26B A4B IT vs North Mini Code 1.0
- Gemma 4 31B IT vs North Mini Code 1.0
- Gemma 4 E2B IT vs North Mini Code 1.0
- Gemma 4 E4B IT vs North Mini Code 1.0
- GLM-4.5-Air vs North Mini Code 1.0
- GLM-4.7-Flash vs North Mini Code 1.0
- GLM-5.3-Flash vs North Mini Code 1.0
- GLM-5.3 vs North Mini Code 1.0
- gpt-oss-120b vs North Mini Code 1.0
- gpt-oss-20b vs North Mini Code 1.0
- Granite 4.2 30B vs North Mini Code 1.0
- Granite 4.2 3B vs North Mini Code 1.0
- Granite 4.2 8B vs North Mini Code 1.0
- Hy-Memory-30B-A3B vs North Mini Code 1.0
- Hy3 vs North Mini Code 1.0
- Inkling-Small vs North Mini Code 1.0
- Inkling vs North Mini Code 1.0
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs North Mini Code 1.0
- Kimi K3.1 Pro vs North Mini Code 1.0
- Kimi K3 vs North Mini Code 1.0
- Kolibri-1 vs North Mini Code 1.0
- Kronos vs North Mini Code 1.0
- Laguna M.1 vs North Mini Code 1.0
- Laguna S 2.1 vs North Mini Code 1.0
- Laguna XS 2.1 vs North Mini Code 1.0
- LBS-27B vs North Mini Code 1.0
- LFM2.5-2.6B vs North Mini Code 1.0
- LFM3-1.7B vs North Mini Code 1.0
- LFM3-Audio-2B vs North Mini Code 1.0
- LFM3-Omni-2B vs North Mini Code 1.0
- LFM3-VL-2B vs North Mini Code 1.0
- Ling-3.0-tiny vs North Mini Code 1.0
- Ling-3.1-flash-1019 vs North Mini Code 1.0
- LongCat-2.5 vs North Mini Code 1.0
- MiMo-V2.6 Distill Qwen 9B vs North Mini Code 1.0
- MiMo-V2.6-Flash-RL vs North Mini Code 1.0
- MiniCPM-o 4.5 vs North Mini Code 1.0
- MiniCPM-V 4.7 1B vs North Mini Code 1.0
- MiniCPM-V 4.7 35B-A3B vs North Mini Code 1.0
- MiniCPM5-2B vs North Mini Code 1.0
- MiniMax-M2.5 vs North Mini Code 1.0
- MiniMax-M2.7 vs North Mini Code 1.0
- MiniMax-M3.1-Flash vs North Mini Code 1.0
- Mistral Large 4 vs North Mini Code 1.0
- Muse Glimmer 30B vs North Mini Code 1.0
- Nanbeige4.2-3B vs North Mini Code 1.0
- Nanbeige4.3-33B vs North Mini Code 1.0
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs North Mini Code 1.0
- Nemotron 3.5 Lightning 30B A3B vs North Mini Code 1.0
- Nemotron 3 Nano 30B A3B vs North Mini Code 1.0
- Nemotron 3 Nano 4B vs North Mini Code 1.0
- Nemotron 3 Nano Omni 30B A3B Reasoning vs North Mini Code 1.0
- Nemotron 3 Super 120B A12B vs North Mini Code 1.0
- Nemotron 3 Ultra 550B A55B vs North Mini Code 1.0
- North Mini Code 1.0 vs occamy-1.0
- North Mini Code 1.0 vs Olmo 3 7B Think
- North Mini Code 1.0 vs Ornith-1.5-122B
- North Mini Code 1.0 vs Ornith-1.5-35B-A3B
- North Mini Code 1.0 vs Ornith-1.5-397B
- North Mini Code 1.0 vs Ornith-1.5-9B
- North Mini Code 1.0 vs OTel-2.0-LLM-31B-IT
- North Mini Code 1.0 vs Qwen-AgentWorld-35B-A3B
- North Mini Code 1.0 vs Qwen3-30B-A3B-Instruct-2507
- North Mini Code 1.0 vs Qwen3-4B-Instruct-2507
- North Mini Code 1.0 vs Qwen3.5-0.8B
- North Mini Code 1.0 vs Qwen3.5-122B-A10B
- North Mini Code 1.0 vs Qwen3.5-2B
- North Mini Code 1.0 vs Qwen3.5-397B-A17B
- North Mini Code 1.0 vs Qwen3.5-4B
- North Mini Code 1.0 vs Qwen3.5-9B
- North Mini Code 1.0 vs Qwen3.6-27B
- North Mini Code 1.0 vs Qwen3.6-35B-A3B
- North Mini Code 1.0 vs Qwen3.8-27B
- North Mini Code 1.0 vs Qwen3.8-Flash-Next
- North Mini Code 1.0 vs Qwen3-Coder-30B-A3B-Instruct
- North Mini Code 1.0 vs Qwen3-Coder-Next
- North Mini Code 1.0 vs Qwen3-Omni-30B-A3B-Instruct
- North Mini Code 1.0 vs Qwen3-VL-2B-Instruct
- North Mini Code 1.0 vs Qwen3-VL-30B-A3B-Instruct
- North Mini Code 1.0 vs Qwen3-VL-32B-Instruct
- North Mini Code 1.0 vs Qwen3-VL-4B-Instruct
- North Mini Code 1.0 vs Qwen3-VL-8B-Instruct
- North Mini Code 1.0 vs Qwopus3.8-27B-Flash-V2
- North Mini Code 1.0 vs Recursive Flint
- North Mini Code 1.0 vs Ripple-65B Preview
- North Mini Code 1.0 vs SenseNova-Loop-9B-Preview
- North Mini Code 1.0 vs SmolLM3-3B
- North Mini Code 1.0 vs Spark-X2.6-4B
- North Mini Code 1.0 vs Step 3.7 Flash
- North Mini Code 1.0 vs Swift 1.5 Qwen3.8-27B
- North Mini Code 1.0 vs Swift 1.5 Qwen3.8-Flash-Next
- North Mini Code 1.0 vs ThinkingCap (Qwen3.8 27B)
- North Mini Code 1.0 vs Baidu Unlimited-OCR-2
- North Mini Code 1.0 vs WeVisOne-VL-2B
- North Mini Code 1.0 vs WeVisOne-VL-4B
- North Mini Code 1.0 vs ZAYA1-8B
Machine-readable
- This page as Markdown
/compare/deepseek-v3-2-vs-north-mini-code-1-0.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/deepseek-v3-2.json·/api/v1/tools/north-mini-code-1-0.json - From a terminal
anchor compare deepseek-v3-2 north-mini-code-1-0(the CLI) - Over MCP
compare_tools {"a": "deepseek-v3-2", "b": "north-mini-code-1-0"}at/mcp, no key