Data as of October 23, 2026 · How the score is built
Nemotron 3.5 Bolt E4B BF16
Decision readingNemotron 3.5 Bolt E4B BF16 is tracked, but not publicly ranked yet. The profile exposes 19 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Oct 23, 2026 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
Unranked
field median 49.9Not eligible for a public rank
Price
API rate not published
input median $0.75No comparable first-party hosted token rate
Speed
Not measured
field median 93 tok/sTime to first token not measured
Context
64Ktokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Published rows are visible, but no category has enough eligible evidence for a comparative rank.
Validate before choosing
19 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 19 displayable benchmark rows
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticWeight 22%5 benchmarksVerified | Score pending | 5 benchmarks | Verified | |||
| CodingWeight 20%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| ReasoningRank Not rankedWeight 17%3 benchmarksVerified | 29.0 | 3 benchmarks | Verified | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeWeight 12%2 benchmarksVerified | Score pending | 2 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%9 benchmarksVerified | Score pending | 9 benchmarks | Verified | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
19 of 764 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic5/5 verified
- CodingNot measured
- Reasoning3/3 verified
- MultimodalNot measured
- Knowledge2/2 verified
- MultilingualNot measured
- Inst. Following9/9 verified
- MathNot measured
Benchmark ledger
Agentic opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Agentic5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| BFCL v3Berkeley Function Calling Leaderboard v3 | Score68.5% | Versus best verified row Best verified: Ternary Bonsai 2 27B · 74.9% | Gap6.4 behind | WeightDisplay only | Provider exact |
| When2Call Multi-TurnWhen2Call Multi-Turn (NVIDIA) | Score63.36% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B BF16 · 63.36% | GapBest verified | WeightDisplay only | Provider exact |
| ToolSandbox | Score68.77% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B · 74.13% | Gap5.4 behind | WeightDisplay only | Provider exact |
| τ²-bench resultsτ²-Bench Tool-Agent-User Evaluation | Score55.1% | Versus best verified row Best verified: GPT-5.4 · 98.9% | Gap43.8 behind | WeightDisplay only | Provider exact |
| RelyToolBench | Score63.16% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B · 69.29% | Gap6.1 behind | WeightDisplay only | Provider exact |
Reasoning3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| LongBench v2 | Score50.5% | Versus best verified row Best verified: Beam 1.0 501B-A23B FP8 · 67.6% | Gap17.1 behind | WeightWeighted 25% | Provider exact |
| RULER (64K)RULER at a 64K-token context | Score86.99% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B BF16 · 86.99% | GapBest verified | WeightDisplay only | Provider exact |
| LongMemEval | Score72.10% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B BF16 · 72.10% | GapBest verified | WeightDisplay only | Provider exact |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| GaRAGe | Score42.61% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B BF16 · 42.61% | GapBest verified | WeightDisplay only | Provider exact |
| RAGTruth (provider reports)RAGTruth: provider-reported F1 | Score77.59% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B · 77.88% | Gap0.3 behind | WeightDisplay only | Provider exact |
Inst. Following9 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MultiChallenge (provider reports)MultiChallenge: provider-reported runs | Score53.10% | Versus best verified row Best verified: Mercury 3 · 60.35% | Gap7.3 behind | WeightDisplay only | Provider exact |
| Brevity BenchmarkBrevity Benchmark (NVIDIA) | Score82.52% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B · 82.84% | Gap0.3 behind | WeightDisplay only | Provider exact |
| RoleBenchRoleBench (RoleLLM) | Score67.05% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B · 71.21% | Gap4.2 behind | WeightDisplay only | Provider exact |
| RoleMRC | Score80.63% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B BF16 · 80.63% | GapBest verified | WeightDisplay only | Provider exact |
| IHEvalIHEval: instruction hierarchy evaluation | Score84.79% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B BF16 · 84.79% | GapBest verified | WeightDisplay only | Provider exact |
| AgentIFAgentIF: instruction following in agentic scenarios | Score25.81% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B BF16 · 25.81% | GapBest verified | WeightDisplay only | Provider exact |
| InverseIFEval | Score46.84% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B BF16 · 46.84% | GapBest verified | WeightDisplay only | Provider exact |
| StructEval-TStructEval text-format subset | Score80.40% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B BF16 · 80.40% | GapBest verified | WeightDisplay only | Provider exact |
| SysBenchSysBench: system message following | Score67.88% | Versus best verified row Best verified: Nemotron 3.5 Bolt E4B BF16 · 67.88% | GapBest verified | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 19 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- Weights model ID
- nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16NVIDIA BF16 model card
- Context window
- 64KNVIDIA BF16 model card
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- textNVIDIA BF16 model card
- Output modalities
- textNVIDIA BF16 model card
- Parameters
- Not sourced yet
- Availability
- Hugging Face · self-hosted inferenceNVIDIA BF16 model card
- Cloud regions
- Not tracked yet
- Lifecycle
- activeNVIDIA BF16 model card
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordNVIDIA Hugging Face model card
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Nemotron 3.5 Bolt E4B BF16, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Nemotron 3.5 Bolt E4B BF16 is a open weight model with a 64K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Open BF16 weights for vLLM serving, customization and post-training. The 4GB Q4_K_M checkpoint is the release NVIDIA documents for local inference.
NVIDIA released the unquantized BF16 checkpoint on October 23, 2026 under OpenMDW 1.1 alongside the 4GB release: the same Gemma 4 E4B-based model with 8B total and 4B effective parameters, published for customization, post-training and evaluation rather than for 4GB local inference. The card lists text in and text out with a 64K-token context. Benchmark values are NVIDIA-reported runs of this BF16 checkpoint, the column NVIDIA's research page also shows; the Q4_K_M column stays on the released model's row. NVIDIA ran every listed benchmark itself in its NeMo Gym harness, in reasoning mode except RoleBench, EQ-Bench v3 and RULER. MultiChallenge, BFCL v3, Tau2-Bench and LongBench v2 (truncated to 48K tokens) use existing lanes; the other sixteen launch benchmarks are stored on their own display-only keys, including Brevity Benchmark and When2Call Multi-Turn, which NVIDIA says it will release later. IFBench is reported as prompt-level loose accuracy and stays unmapped, as it did for the 74B-A9B release. NVIDIA's Gemma 4 E4B, Qwen3.5 4B and Nemotron 3 Nano 4B comparison columns are not copied onto other rows. This reference checkpoint is tracked beside the 4GB release and does not receive a second family rank.
Nemotron 3.5 Bolt E4B BF16 sits in the Nemotron 3.5 Bolt E4B family with Nemotron 3.5 Bolt E4B. 19 of 764 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated October 23, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does Nemotron 3.5 Bolt E4B BF16 perform overall in AI benchmarks?
Nemotron 3.5 Bolt E4B BF16 has 19 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.
Is Nemotron 3.5 Bolt E4B BF16 good for knowledge and understanding?
Nemotron 3.5 Bolt E4B BF16 has source-displayable benchmark coverage for knowledge and understanding, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Nemotron 3.5 Bolt E4B BF16 good for reasoning and logic?
Nemotron 3.5 Bolt E4B BF16 has source-displayable benchmark coverage for reasoning and logic, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Nemotron 3.5 Bolt E4B BF16 good for agentic tool use and computer tasks?
Nemotron 3.5 Bolt E4B BF16 has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Nemotron 3.5 Bolt E4B BF16 good for instruction following?
Nemotron 3.5 Bolt E4B BF16 has source-displayable benchmark coverage for instruction following, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Nemotron 3.5 Bolt E4B BF16 open source?
Nemotron 3.5 Bolt E4B BF16 is an open-weight model from NVIDIA. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Which sibling models are related to Nemotron 3.5 Bolt E4B BF16?
Nemotron 3.5 Bolt E4B BF16 belongs to the Nemotron 3.5 Bolt E4B family. Related tracked variants include Nemotron 3.5 Bolt E4B. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Nemotron 3.5 Bolt E4B BF16 have full benchmark coverage on BenchLM?
No. Nemotron 3.5 Bolt E4B BF16 currently has 20 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Nemotron 3.5 Bolt E4B BF16?
Nemotron 3.5 Bolt E4B BF16 has a documented context window of 64K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.