Primary sources last checked on 13 Nov 2026. Verification freshness is tracked separately from factual change, and unknown values remain explicit rather than inferred.
NotableCurrent Mistral Small 4 representative with independent Artificial Analysis coverage.Curation method →
Open Model Weights records Mistral Small 4 119B A6B as a 119B total / 6.5B active-parameter text + image → text open-weight model in the Mistral Small 4 family, with Mistral AI listed as the developer. The checked source repository provides 12 recognized weight artifacts, format evidence for Safetensors and a verified context window of 1,048,576 tokens. Values that are not evidenced in the checked sources remain explicitly undisclosed or unknown.
The repository declares apache-2.0. Commercial use allowed under apache-2.0 conditions. Open Model Weights reports the checked license evidence and classification; this is not legal advice.
No base model is declared in the checked standard lineage metadata, so Open Model Weights does not infer one. Training recipe status: training-described-in-model-card; data disclosure status: not-disclosed-in-standard-metadata-or-obvious-model-card-section.
Mistral Small 4 119B A6B is sparse 119B-A6B Mistral model combining text and image inputs with a very long configured context. OMW checked the public source repository for 119B observed published parameter values, 1,048,576 configured context tokens, and a apache-2.0 license declaration. The official model card mentions Mistral Common and multiple serving backends. Tokenization and conversation templates matter especially for tool-oriented prompts; a backend being mentioned is not equal to successful execution with this exact variant. Its Notable badge is a separate editorial discovery signal, not a performance measurement by OMW.
Primary technical focussparse 119B-A6B Mistral model combining text and image inputs with a very long configured contextSource ↗
Weight metadata119B observed published parameter valuesSource ↗
Checked context evidence1,048,576 tokens declared in checked config.jsonSource ↗
Source license statusapache-2.0 (allowed commercial-use classification from checked source)Source ↗
Runtime evidence classPublisher/source mentions only; no OMW execution testSource ↗
WHY IT MATTERS
The source checkpoint exposes approximately 119.4 billion parameter values and a 1,048,576-token config field. The A6B suffix is a publisher model designation, not an OMW measurement of activations per token.
The open-weight small-family branding should not lead readers to assume it is lightweight. It remains a large total-weight checkpoint; teams should compare peak memory and sharding costs against smaller 20–30B-class vision-language alternatives.
MODEL-SELECTION VIEW
Strong fit when…
The open-weight small-family branding should not lead readers to assume it is lightweight. It remains a large total-weight checkpoint; teams should compare peak memory and sharding costs against smaller 20–30B-class vision-language alternatives.
Evaluations that require sparse 119B-A6B Mistral model combining text and image inputs with a very long configured context and an inspectable original weight/source revision.
Important considerations
The model metadata declares Apache-2.0, while the checked snapshot does not independently include a repository LICENSE file. Source of the license claim should be shown precisely.
Check tokenizer and multimodal processor compatibility, quantify precision-specific GPU memory and run real long-context throughput tests before sizing hardware.
Architecture and task-specific behavior
The source checkpoint exposes approximately 119.4 billion parameter values and a 1,048,576-token config field. The A6B suffix is a publisher model designation, not an OMW measurement of activations per token.
The official model card mentions Mistral Common and multiple serving backends. Tokenization and conversation templates matter especially for tool-oriented prompts; a backend being mentioned is not equal to successful execution with this exact variant.
Verified configuration versus usage claims
The primary registry record identifies Mistral Small 4 119B A6B as Text + image → text. The checked configuration lists 1,048,576 tokens. This value is a declared configuration bound, not a measured practical prompt limit. This page treats a checked config field, the model-card prose and a deployment benchmark as three distinct kinds of evidence.
In the current checked snapshot, 119B observed published parameter values are recorded with a source repository revision. Those weight-parameter values do not determine how much GPU memory, active compute or KV-cache is required by a real application; sparse activation, quantization and runtime overhead each need separate verification.
What the actual weight repository contains
OMW checked 12 recognized weight artifacts in Safetensors format. The 119B observed published parameter values come from the published repository data, not from a newly executed OMW performance test. A file count is not a checksum audit, a full weight-binary comparison or a statement about throughput.
The source revision and exact listed weight files can be inspected through the linked OMW evidence API and the official model repository. Before distributing or deploying a model, pin the precise commit and independently validate downloaded artifact checksums where available. An upstream revision change must not automatically be described as changed weight bytes.
License and intended commercial deployment
The source declares apache-2.0; its commercial classification is allowed under the stated license conditions. Read the actual terms and any attribution obligations before shipping. Source observation does not provide legal advice.
The model metadata declares Apache-2.0, while the checked snapshot does not independently include a repository LICENSE file. Source of the license claim should be shown precisely. Keep publisher license declarations separate from third-party interpretations, custom usage agreements and any deployment-specific regulatory obligations. Where a permission is unknown, the registry intentionally reports unknown rather than guessing a permissive answer.
Runtime, hardware and reproduction limits
The source record includes Mistral Common, SGLang, Transformers, llama.cpp, vLLM as declared libraries or model-card mentions. This is provenance-aware compatibility information only: OMW has not executed a model load, generated outputs or benchmarked the exact checkpoint on a specified GPU. Runtime support for a particular version, precision and processor remains to be tested.
Check tokenizer and multimodal processor compatibility, quantify precision-specific GPU memory and run real long-context throughput tests before sizing hardware. The generic weight-only memory estimate in the model snapshot does not include multimodal processors, activation buffers, temporary tensors, cache growth, device placement or kernel availability; these can dominate real deployments.
When to choose this model and how to compare it
The open-weight small-family branding should not lead readers to assume it is lightweight. It remains a large total-weight checkpoint; teams should compare peak memory and sharding costs against smaller 20–30B-class vision-language alternatives.
For a fair comparison, choose another model from the same task family and freeze the task dataset, prompt or preprocessing settings, tested checkpoint revisions and compute budget. The model metadata declares Apache-2.0, while the checked snapshot does not independently include a repository LICENSE file. Source of the license claim should be shown precisely. A Leading or Notable label remains a discovery cue rather than a universal model ranking or an OMW benchmark result.
IMPLEMENTATION & EVALUATION
How to evaluate Mistral Small 4 119B A6B before deployment
Use these as proposed acceptance tests rather than OMW-confirmed performance results. The objective is to establish whether the exact Mistral Small 4 119B A6B revision is legal to use and deployable for a specific workload.
STEP 01
Freeze model artifacts and license evidence
Record the official Mistral Small 4 repository SHA, recognized Safetensors artifacts and the apache-2.0 license evidence before attempting an installation.
REPRODUCIBLE ACCEPTANCE TEST
An immutable source revision, artifact manifest, checksums where available and dated license record are saved together.
WHAT CAN GO WRONG
Mutable model branches or unreviewed third-party weight conversions can silently change the experiment or applicable terms.
STEP 02
Reproduce the documented task interface
The source checkpoint exposes approximately 119.4 billion parameter values and a 1,048,576-token config field. The A6B suffix is a publisher model designation, not an OMW measurement of activations per token.
REPRODUCIBLE ACCEPTANCE TEST
The intended Text + image → text workload runs under a documented processor or tokenizer path with exact dependency versions, or the failure is recorded.
WHAT CAN GO WRONG
The model metadata declares Apache-2.0, while the checked snapshot does not independently include a repository LICENSE file. Source of the license claim should be shown precisely.
STEP 03
Measure deployment and model-specific outputs
Check tokenizer and multimodal processor compatibility, quantify precision-specific GPU memory and run real long-context throughput tests before sizing hardware.
REPRODUCIBLE ACCEPTANCE TEST
Raw evaluation inputs, response or media outputs, memory high-water mark, request latency and error logs are retained and the environment can be reconstructed.
WHAT CAN GO WRONG
Publisher benchmark claims and parameter-derived estimates are not interchangeable with measurements on the chosen hardware.
STEP 04
Compare against a relevant verified alternative
The open-weight small-family branding should not lead readers to assume it is lightweight. It remains a large total-weight checkpoint; teams should compare peak memory and sharding costs against smaller 20–30B-class vision-language alternatives.
REPRODUCIBLE ACCEPTANCE TEST
Run the same tasks and quality rubric against gemma-4-26B-A4B-it and gpt-oss-120b, with source revisions and test limitations disclosed.
WHAT CAN GO WRONG
A different license, modality, processor or sampling budget makes a naive head-to-head score misleading.
Questions people ask about Mistral Small 4 119B A6B.
What is Mistral Small 4 119B A6B designed to do?
Mistral Small 4 119B A6B is sparse 119B-A6B Mistral model combining text and image inputs with a very long configured context. The source checkpoint exposes approximately 119.4 billion parameter values and a 1,048,576-token config field. The A6B suffix is a publisher model designation, not an OMW measurement of activations per token.
What is the verified context length for Mistral Small 4 119B A6B?
The checked configuration lists 1,048,576 tokens. This value is a declared configuration bound, not a measured practical prompt limit.
How big are the published Mistral Small 4 119B A6B weights?
119B observed published parameter values; 12 recognized repository weight entries (Safetensors). This is a weight-metadata observation, not a GPU memory measurement.
Can Mistral Small 4 119B A6B be used commercially?
The source declares apache-2.0; its commercial classification is allowed under the stated license conditions. Read the actual terms and any attribution obligations before shipping. Source observation does not provide legal advice.
Which inference runtimes support Mistral Small 4 119B A6B?
The checked model documentation mentions Mistral Common, SGLang, Transformers, llama.cpp, vLLM. OMW has not run this checkpoint under those runtimes; compatibility must be reproduced for the selected revision.
How should Mistral Small 4 119B A6B be benchmarked?
Check tokenizer and multimodal processor compatibility, quantify precision-specific GPU memory and run real long-context throughput tests before sizing hardware. Keep environment, source commit, data and evaluation method fixed, and distinguish publisher results from your own repeatable tests.
03 · PRACTICAL TECHNICAL PROFILE
Deployment, licensing and reproducible evidence.
Inspect weight-memory estimates, model lineage and runtime evidence separately from promotional or untested performance claims.
DEPLOYMENT PROFILE
Weight memory, without pretending it is a deployment guarantee.
These bars visualize weight-only decimal-GB estimates. They exclude KV cache, activations, runtime overhead, optimizer state and sharding.
WEIGHT-ONLY MEMORY
BF16 / FP16~238.8 GB
FP8 / INT8~119.4 GB
INT4~59.7 GB
FIELD EVIDENCE MAP
WeightsVerified
LicenseVerified
Commercial useAllowed
ContextVerified
FormatsVerified
LineageNot declared
Training recipeTraining described in model card
Training dataNot disclosed in standard metadata or obvious model card section
RuntimeSource-derived · not runtime-tested
LICENSE & USE
apache-2.0
Commercial use allowed under apache-2.0 conditions
Declared licenseapache-2.0
ClassificationAllowed
VerificationDeclared metadata checked
This section summarizes the checked repository evidence. It is not legal advice.
LINEAGE & PROVENANCE
What the checked sources disclose — and what they do not.
Open Model Weights does not infer a hidden base model or training corpus when the checked sources do not declare one.
LINEAGE
BASE / PARENTNot declared in model-card metadataUnknown
not inferred
CURRENT RECORDMistral Small 4 119B A6BMistral Small 4
TRAINING DISCLOSURE
Training recipeTraining described in model card
Training dataNot disclosed in standard metadata or obvious model card section
FamilyMistral Small 4
RUNTIME SIGNALS
Compatibility claims stay attached to their evidence level.
Declared and model-card-mentioned runtimes are discovery signals. They are not treated as Open Model Weights runtime tests unless explicitly measured.
MentionedMistral Common
MentionedSGLang
MentionedTransformers
Mentionedllama.cpp
MentionedvLLM
OMW runtime testNot performed
EVIDENCE TRAIL
Sources and observed history.
This is where the article remains auditable: source links on one side, the registry's observed change history on the other.
Mistral Small 4 119B A6B: technical evidence at a glance
Three evidence-linked visual summaries: parameter scale, illustrative precision memory and verifiable provenance. No performance ranking is implied.
01 / PARAMETER SCALE
Total versus active parameters
Total parameters119.4B
Active parameter count not established.
Repository-derived or publisher-described parameter count
Published total parameters are not a model-quality or performance score.
02 / MEMORY ESTIMATE
Weight-only precision footprint
BF16 / FP16238.8 GB
FP8 / INT8119.4 GB
INT459.7 GB
Hypothetical weight-only decimal GB, not measured peak VRAM or guaranteed support for each format. KV cache, activations, runtime and sharding are excluded.
Weight artifacts12 recognized artifacts · public access
03
License declarationapache-2.0Metadata declaration
04
Latest published source check
Repository SHA a11f36bebf70…; a source check is not an inference benchmark or legal clearance. See the per-model evidence JSON for the exact source record.
A verification check does not pretend the model changed. Open Model Weights updates the verification date after a real primary-source check, while factual-update dates move only when retained source evidence changes.
Commercial useCommercial use allowed under apache-2.0 conditions
Repository license filesNone observed
Classification describes the checked license terms; it is not legal advice.
03 · HARDWARE
Weight-memory estimate
BF16 / FP16~238.8 GB
FP8 / INT8~119.4 GB
INT4~59.7 GB
Weight-only decimal-GB estimate from total parameter count; excludes KV cache, activations, runtime overhead, optimizer state and sharding.
04 · FORMATS
Formats & precision evidence
Safetensors
BF16: not observedFP16: not observedFP8: not observedINT8: not observedINT4: not observedGGUF: not observed
“Not observed” means no matching repository artifact/name/dtype signal was found; it does not prove no third-party conversion exists.
05 · LINEAGE
Base model & family
FamilyMistral Small 4
Variant119B-A6B
Declared base modelNot declared in model-card metadata
RelationNot declared
06 · TRAINING ASSETS
Recipe & data disclosure
Training recipetraining-described-in-model-card
Data disclosurenot-disclosed-in-standard-metadata-or-obvious-model-card-section
EvaluationsNot classified by automated verifier
Intermediate checkpointsNot classified by automated verifier
07 · RUNTIME SUPPORT
Declared, mentioned and externally evidenced runtimes
Declared libraryNot declared
Declared/taggedNone
Mentioned in model cardMistral Common, SGLang, Transformers, llama.cpp, vLLM
Artifact signalsNone
External primary runtime evidenceNone
Tested by Open Model WeightsNo — source-derived support only
Open Model Weights separates model-repository evidence from external runtime-release evidence. An external support statement does not change the official model repository's weight formats and does not imply an Open Model Weights inference benchmark.
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Field-by-field verification
Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.
Field-by-field verification
Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Field-by-field verification
Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.
Registry record created
Previous verification level: verified.
licenseverified
commercial useclassified
contextverified
weight filesverified
formatsverified
base modelnot-declared
training recipetraining-described-in-model-card
data disclosurenot-disclosed-in-standard-metadata-or-obvious-model-card-section
runtime supportsource-derived-not-runtime-tested
MODELS FOR AI AGENTS · ROLE EVIDENCE
Where this model fits in an agent system
Multimodal reasoning model. A candidate for a reasoning or coordination role. No end-to-end agent performance is inferred from its model category.
The curated notable tier is not an agent-readiness rating. Model-specific tool-call success, long-horizon task accuracy and compatible runtime configurations are not independently established here.
Source-linked license: apache-2.0 (allowed commercial-use classification; see original terms).
Context: 1048576 configured tokens.
BF16 weights: 238.8 estimated decimal GB, not runtime VRAM.
These records are separately sourced. They do not replace independent model-plus-runtime tests.
Tool calling · publisher-documented — Mistral's first-party model card documents native function calling and JSON output and provides a vLLM command with the Mistral tool parser. Original source ↗
vLLM · publisher setup documented — Publisher's full serving command; not an OMW runtime test. Hardware and installed version must be validated. Original source ↗