Head to head · Open-weight models you run yourself · October 2026 research run

DeepSeek-V3.2 vs Inkling 2 Mini

Inkling 2 Mini scores 61 (C) on agent readiness against DeepSeek-V3.2's 58.6 (C), and leads in 3 of 4 scored categories. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6586 open weights comparisons

Which one, for what

DeepSeek-V3.2 C

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

Inkling 2 Mini C

Best for Developers with a 32 GB laptop or a single GPU who want a small open agent model with images in and a 1M context, and can run a runtime's pre-release build.

Ahead on

  • Risk, 70 against 50
  • Agent interface, 85 against 60
  • Documentation and upkeep, 57 against 34

Watch for

No released version of vLLM, SGLang, Transformers, llama.cpp or Ollama runs it on 20 November 2026

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.

Agent interface Inkling 2 Mini +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.

Inkling 2 Mini 85

Chat template 20, chat_template.jinja in the repository. Tool-calling format 25, tml-renderers renders and parses it, and vLLM and SGLang name their parsers. Trained tool calling 20, several calls in one turn. Structured output 0, not documented. Reasoning control 10, reasoning_effort per request. Context 10, 1M trained. 20 + 25 + 20 + 0 + 10 + 10 = 85.

Documentation and upkeep Inkling 2 Mini +23

DeepSeek-V3.2 34

The model card earns 14 when read with DeepSeek's own V3.2 model card PDF, which adds intended use and a parameter count, leaving languages and a knowledge cut-off missing. Training data earns 5, a general description with no cut-off. Last change earns 5, as nothing in the repository has changed since 1 December 2025 (338 days on 4 November) and DeepSeek's deepseek-recipe has no V3.2 code. Responsiveness earns nothing, with no reply from a deepseek-ai member in any of the 40 most recent discussions. Version policy earns 5 for earlier versions kept apart without dated notes. File health earns 5 because loading and parsing reports wait without a reply.

Inkling 2 Mini 57

Model card 17, no knowledge cut-off. Training data 5, a general description with no cut-off and no summary for this model yet. Last change 20, uploaded today. Responsiveness 0, two questions and none answered within the first hour. Version policy 5, a first release. File health 10, the files and the card agree. 17 + 5 + 20 + 0 + 5 + 10 = 57.

Risk Inkling 2 Mini +20

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.

Inkling 2 Mini 70

File safety 25, safetensors only and no repository code to run. Provenance 15, the files are in the organisation Thinking Machines links to, with a SHA-256 on every LFS file. Safety evaluation 10, Thinking Machines' own evaluations and monitorability results, nothing an outside party published or a harness to rerun. Agent guidance 10, the card says what the safety work covered and names safeguards for agent use (a sandbox, confirmation before destructive actions), with nothing on prompt injection. Licence risk 5, 10 off for a use policy that reaches beyond the law and that can change at any time. Security 5, security.txt and a disclosure policy. 25 + 15 + 10 + 10 + 5 + 5 = 70.

Score by category

CategoryWeightDeepSeek-V3.2Inkling 2 MiniEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%6060even
Risk20%5070Inkling 2 Mini +20
Agent interface10%6085Inkling 2 Mini +25
Documentation and upkeep10%3457Inkling 2 Mini +23
Negative events≤1500
TotalC 58.6/100C 61/100

Facts side by side

FactDeepSeek-V3.2Inkling 2 Mini
KindOpen-weight modelOpen-weight model
VendorDeepSeekThinking Machines Lab
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceMITApache-2.0
Read-only variant documentednono
llms.txtnono
Last release2025-12-012026-11-20
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews2.3/5 (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.

Inkling 2 Mini

Thinking Machines' small open model, a looped 26.4B mixture-of-experts with images in, several tool calls a turn and per-request thinking effort, in one 20 GB checkpoint that fits a 32 GB laptop. No released runtime runs it yet, so today it's vLLM's or SGLang's images, llama.cpp from master, or Tinker.

Before you call either

DeepSeek-V3.2

  1. 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
  2. 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
  3. 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
  4. Pick thinking or chat with thinking_mode, and read the reasoning from reasoning_content
  5. Send developer messages only for search-agent prompts, the only use DeepSeek gives that role
  6. Use temperature 1.0 and top_p 0.95 and keep prompts within 128K tokens

Inkling 2 Mini

  1. No released runtime runs it yet. Serve it from vLLM's vllm/vllm-openai:inkling-2-mini image with --reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling, or from SGLang's lmsysorg/sglang:inkling-2-mini image, where the tool-call parser is inkling2
  2. On a laptop, ggml-org's GGUF runs in a llama.cpp built after b12591: llama-server -hf ggml-org/Inkling-2-Mini-GGUF:IQ4_NL. The looped architecture isn't in a llama.cpp release yet
  3. Pass reasoning_effort as none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99. The minimum doesn't fully turn reasoning off
  4. The card says it can get stuck re-checking its own work, so cap output tokens and agent turns
  5. Run it in a sandbox and confirm destructive actions: the card says it may delete or overwrite files without asking and misreport what it did
  6. Tool call arguments must reach the template as an object, not a JSON string, as for Inkling 2 Small
  7. Images should be 40 to 4096 px a side. It takes no audio, and the template raises an error for an audio part
  8. Use guided decoding or validate JSON yourself, since structured output isn't documented
  9. Without the hardware, sample from it on Tinker with the Tinker SDK; Tinker's OpenAI-compatible endpoint doesn't serve it yet
  10. Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal

Questions

Which is better for AI agents, DeepSeek-V3.2 or Inkling 2 Mini?

Inkling 2 Mini scores 61 (C) on agent readiness against DeepSeek-V3.2's 58.6 (C), and leads in 3 of 4 scored categories.

Other comparisons with DeepSeek-V3.2 or Inkling 2 Mini

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.