Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Ricoh / Ricoh LMM

Qwen3.6-Ricoh-27B-20260522

Japanese multimodal reasoning model with original, 8-bit and 4-bit configurations for private deployment.

Language models (LLMs)Document extraction / OCR
previewClosed weightsGeneral purposeDocument understanding
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
9 of 19 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingSee billing notesRicoh starter kit (announced)
Output billingSee billing notesAccess and billing notes below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)

Document images and text are demonstrated. Generic descriptions of LMMs do not establish audio/video support for this model.

Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
SupportedSource for Reasoning (opens in a new tab)
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
SupportedSource for Fine-tuning (opens in a new tab)

Provider describes customer-specific training or adaptation for private deployment, not a public self-service fine-tuning API.

Knowledge cutoff
Not collected
Release date
2026-06-05Source for Release date (opens in a new tab)

Public announcement date, not a date inferred from the model ID.

Parameters
27BSource for Parameters (opens in a new tab)
Architecture
Not collected
Languages
JapaneseSource for Languages (opens in a new tab)

Documented focus; not an exhaustive supported-language list.

Context caching
Not collected

No model-specific prompt-cache contract, lifetime or cached-input price verified. Quantization and image-token compression are not prompt caching.

Published price
Individual deployment quoteSource for Published price (opens in a new tab)

Starter-kit pricing depends on installation environment and requirements. Hardware, setup, support and model terms must be confirmed; no USD/token or per-question rate is established.

Base model
Qwen3.6-27BSource for Base model (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Ricoh starter kit (announced)

Provider source (opens in a new tab)
API model ID
Not collected

Published model name is not a verified API request selector.

Access
Announced June 5 with starter-kit availability planned for late June. The captured current lineup still says planned; a completed commercial rollout for this exact model is not verified.
Regions
Customer-selected private environment; region and residency depend on the deployment agreement.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Ricoh private deployment (AWQ)

Provider source (opens in a new tab)
API model ID
Not collected

Published model name is not a verified API request selector.

Access
Documented Qwen3.6-Ricoh-27B-20260522-AWQ-W8A16 configuration. Public rollout, price and API contract remain unverified.
Regions
Customer-selected private environment; region and residency depend on the deployment agreement.
Quantization and compression
AWQ-W8A16Source for Quantization and compression (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Ricoh private deployment (AWQ)

Provider source (opens in a new tab)
API model ID
Not collected

Published model name is not a verified API request selector.

Access
Documented Qwen3.6-Ricoh-27B-20260522-AWQ-W4A16 configuration. Public rollout, price and API contract remain unverified.
Regions
Customer-selected private environment; region and residency depend on the deployment agreement.
Quantization and compression
AWQ-W4A16Source for Quantization and compression (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Ricoh starter kit (announced)

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

Ricoh private deployment (AWQ)

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

Ricoh private deployment (AWQ)

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

What the measurements say

JDocQA-Reasoning / fp16

Ricoh · vendor-reported
0.881score / 1

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

JDocQA / fp16

Ricoh · vendor-reported
4.22score / 5

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

ELYZA-tasks-100 / fp16

Ricoh · vendor-reported
4.64score / 5

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

Japanese MT-Bench / fp16

Ricoh · vendor-reported
9.48score / 10

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

JDocQA-Reasoning / awq-w8a16

Ricoh · vendor-reported
0.873score / 1

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

JDocQA / awq-w8a16

Ricoh · vendor-reported
4.21score / 5

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

ELYZA-tasks-100 / awq-w8a16

Ricoh · vendor-reported
4.65score / 5

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

Japanese MT-Bench / awq-w8a16

Ricoh · vendor-reported
9.47score / 10

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

JDocQA-Reasoning / awq-w4a16

Ricoh · vendor-reported
0.868score / 1

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

JDocQA / awq-w4a16

Ricoh · vendor-reported
4.2score / 5

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

ELYZA-tasks-100 / awq-w4a16

Ricoh · vendor-reported
4.62score / 5

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

Japanese MT-Bench / awq-w4a16

Ricoh · vendor-reported
9.35score / 10

June 2026 Ricoh evaluation, five-run averages; vLLM 0.19.0 for visual tasks and 0.20.1 for text. Azure gpt-4.1 judging except JDocQA uses gpt-4o. JDocQA-Reasoning contains 1,362 cases. Configuration-specific vendor results, not an independent ranking.

Evaluation source (opens in a new tab)

JDocQA-Reasoning single-page / baseline

Ricoh · vendor-reported
0.875score / 1

June 17, 2026 provider evaluation of AWQ-W8A16; 1,208 single-page questions out of 1,362, five-run averages, gpt-4.1-2025-04-14 judge. Workflow adds document analysis and selection; do not treat the pipeline result as native model-only performance.

Evaluation source (opens in a new tab)

JDocQA-Reasoning single-page / workflow

Ricoh · vendor-reported
0.904score / 1

June 17, 2026 provider evaluation of AWQ-W8A16; 1,208 single-page questions out of 1,362, five-run averages, gpt-4.1-2025-04-14 judge. Workflow adds document analysis and selection; do not treat the pipeline result as native model-only performance.

Evaluation source (opens in a new tab)

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Provider identifies this separately trained model for research or private deployment. No matching public derivative was verified in the two provider-linked weight inventories. Closed-weight classification is inferred for this exact revision, not its public upstream base; private distribution terms remain to be confirmed.

Classification evidence (opens in a new tab)

Lifecycle dates

Model announced5 Jun 2026Source (opens in a new tab)

Sources reviewed