Sign in

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

Gemma 4 26B A4B IT vs Kimi K3.1 Pro

Gemma 4 26B A4B IT scores 72.2 (BB) on agent readiness against Kimi K3.1 Pro's 48.6 (D), 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 4969 open weights comparisons

Gemma 4 26B A4B ITGoogle DeepMind · Open-weight model BB72.2/100#5 of 135 open-weight models Kimi K3.1 ProMoonshot AI · Open-weight model D48.6/100#130 of 135 open-weight models

Which one, for what

Gemma 4 26B A4B IT BB

Best for Agents on a 24 GB or larger GPU or Mac that want a fast, permissively licensed tool-calling model with images and long context

Ahead on

  • Reach, 90 against 40
  • Risk, 70 against 50
  • Agent interface, 85 against 65
  • Documentation and upkeep, 65 against 51

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

No safety evaluation figures published

Kimi K3.1 Pro D

Best for Operators with a multi-accelerator node who want Moonshot's newest open-weight model for coding and long agent sessions, and everyone else through an API

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

1,561 GB of files, so it needs a node of eight large accelerators at least

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 Gemma 4 26B A4B IT +50

Gemma 4 26B A4B IT 90

Memory 25, Google's own 4-bit QAT GGUF is 14.4 GB, which with a fifth on top is 17.3 GB and lands in the 24 GB band, with the 1.2 GB vision projector extra for images. Runtimes 25, released support in vLLM, Transformers, llama.cpp, Ollama, SGLang and LM Studio, six of six. Builds 10, Google publishes one quantised precision (Q4_0 GGUF), since its unquantised QAT repository is BF16 and there's no FP8 build. Terms 15, plain Apache 2.0 with nothing added. Download 10, no account or gate. Hosted 5, the Gemini API serves it and four inference providers are live on Hugging Face.

Kimi K3.1 Pro 40

Memory 0, the only build is Moonshot's 1,561 GB MXFP4 release, far above 256 GB. Runtimes 5, llama.cpp b12242 alone has the model code in a release, since vLLM's recipe needs 0.34.0 and SGLang's cookbook a branch. Builds 10, one precision. Terms 10, free commercial use below a model-as-a-service revenue threshold. Download 10, not gated. Hosted 5, Moonshot's API and Together serve it. 0 + 5 + 10 + 10 + 10 + 5 = 40.

Risk Gemma 4 26B A4B IT +20

Gemma 4 26B A4B IT 70

File safety 25, safetensors and GGUF only, with nothing from the repository run on load. Provenance 15, the files sit in Google's own organisation and every file has a checksum. Safety evaluation 0, the card says testing showed minimal policy violations but gives no figures. Agent guidance 10, the card names the harm categories its safety training covers and asks for content-safety safeguards, and the tool guide says to validate calls, with no prompt-injection guidance. Licence risk 15, Apache 2.0 with no added policy, no threshold and a working link. Security programme 5, Google's security.txt and reward policy give a route to report a flaw, but no public Gemma advisories were found and GitHub's advisory tab couldn't be checked.

Kimi K3.1 Pro 50

File safety 15, safetensors only, less 10 for remote code and prompts built by the repository's script. Provenance 15, Moonshot's own organisation with a hash on every file. Safety evaluation 10, Moonshot's own cyber benchmark results and nobody else's yet. Agent guidance 0, none on the card. Licence risk 10, the revenue threshold. Security programme 0, no way to report a flaw found. 15 + 15 + 10 + 0 + 10 + 0 = 50.

Agent interface Gemma 4 26B A4B IT +20

Gemma 4 26B A4B IT 85

Chat template 20, a Jinja file in the repository. Tool-calling format 25, Google documents how tools are declared and how calls come back, ships a response schema for Transformers' parser, and names the gemma4 parser in vLLM and SGLang. Trained tool calling 20, several calls in one turn. Structured output 0, nothing documents how to ask the weights for JSON or a schema. Reasoning control 10, thinking is off by default, turned on per request, and returned in a thought channel. Context 10, 262,144 tokens native.

Kimi K3.1 Pro 65

Chat template 10, the format is only code to run. Tool-calling format 10, the parser is named in the runtimes' recipes and the card doesn't say how tools are declared. Trained tool calling 20, several calls a turn on Kimi K3's tools channel. Structured output 5, named among linked guides without the how. Reasoning control 10, reasoning_effort per request. Context 10, 1M tokens. 10 + 10 + 20 + 5 + 10 + 10 = 65.

Documentation and upkeep Gemma 4 26B A4B IT +14

Gemma 4 26B A4B IT 65

Model card 20, all seven items are there. Training data 10, a general description by type with a January 2025 cut-off and the filtering, but no sources, mix or sizes. Last change 10, the files last changed on 20 July 2026, 104 days before 1 November, still inside 180 days. Responsiveness 10, Google replied to 16 of the 35 questions and reports, and to 1 of the 9 since 23 July, with its newest reply on 1 October. Version policy 10, earlier Gemma generations keep their own repositories and gemma.ai has a dated releases page. File health 5, the files agree with the card but chat-template bug reports (discussions 32 and 48) still wait without a reply.

Kimi K3.1 Pro 51

Model card 11, no limitations, languages or cut-off. Training data 5, one general sentence. Last change 20, a commit on 5 November 2026. Responsiveness 0, none of the 8 newest discussions has a reply from Moonshot. Version policy 5, Kimi K3 keeps its repository and no dated note was found. File health 10, the files agree. 11 + 5 + 20 + 0 + 5 + 10 = 51.

Score by category

CategoryWeight this runGemma 4 26B A4B ITKimi K3.1 ProEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%259040Gemma 4 26B A4B IT +50
Risk20%207050Gemma 4 26B A4B IT +20
Agent interface10%108565Gemma 4 26B A4B IT +20
Documentation and upkeep10%106551Gemma 4 26B A4B IT +14
Negative events≤1500
TotalBB 72.2/100D 48.6/100

Facts side by side

FactGemma 4 26B A4B ITKimi K3.1 Pro
KindOpen-weight modelOpen-weight model
VendorGoogle DeepMindMoonshot AI
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Kimi K3.1 Pro License (modified MIT)
Read-only variant documentednono
llms.txtnono
Last release2026-07-202026-11-05
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews3.8/5 (4)none

Verdicts

Gemma 4 26B A4B IT

A fast mixture-of-experts cousin for general agent work with tools, optional thinking and image input, under Apache 2.0. Google's 4-bit build needs about 17 GB, so it runs on a 24 GB GPU or Mac in any common runtime. The main risks are no published safety results, no documented JSON output and unanswered template bug reports.

Kimi K3.1 Pro

Moonshot's newest flagship, eight days old when read, for operators with a rack. Only llama.cpp has its model code in a release, with vLLM and SGLang support still on a release candidate and a branch. The licence is permissive below a revenue threshold, and Moonshot hasn't answered a discussion on the repository yet.

Before you call either

Gemma 4 26B A4B IT

  1. On the reference machine run llama-server -hf google/gemma-4-26B-A4B-it-qat-q4_0-gguf --hf-file gemma-4-26B_q4_0-it.gguf --jinja -c 65536, and add the mmproj file for images
  2. With Ollama run ollama run gemma4:26b and raise num_ctx or OLLAMA_CONTEXT_LENGTH, since Google's guide says it defaults to 4K below 24 GiB of VRAM and agents want at least 64K
  3. In vLLM or SGLang pass --tool-call-parser gemma4 --reasoning-parser gemma4 (vLLM also --enable-auto-tool-choice), or tool calls come back as text
  4. Thinking is off by default; pass enable_thinking=True or start the system prompt with <|think|>, and drop earlier turns' thinking from history except on tool-call turns
  5. Validate tool names and arguments before running them, and check any JSON yourself

Kimi K3.1 Pro

  1. Use Moonshot's API or Together unless you have a node of eight B300-class accelerators
  2. With vLLM use 0.34.0 or later and the recipe's flags, --tool-call-parser kimi_k3 --reasoning-parser kimi_k3
  3. Pass the whole assistant message back in later turns, reasoning_content and tool_calls included, as the card requires
  4. Set reasoning_effort to low, high or max per request. Max is the default and thinking can't be turned off
  5. Kimi K3's model code doesn't load it, because the attention layers changed
  6. Validate JSON output yourself, since the card doesn't document structured output for the weights

Questions

Which is better for AI agents, Gemma 4 26B A4B IT or Kimi K3.1 Pro?

Gemma 4 26B A4B IT scores 72.2 (BB) on agent readiness against Kimi K3.1 Pro's 48.6 (D), and leads in every scored category.

Other comparisons with Gemma 4 26B A4B IT or Kimi K3.1 Pro

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.

Get an auditSee a sample report