Model datasheet · Nemotron 3
Nemotron 3 Nano 30B-A3B
The long-context specialist of this catalog by a distance: 86.3% on RULER at one million tokens, where most models here are unrated and the best measured rival manages 66% at 128K. A hybrid Mamba-Transformer MoE — only 6 of its 52 layers hold a KV cache, which is why the window is affordable rather than nominal.
- Vendor
- NVIDIA
- Architecture
- MoE · 31.6B total / ~3.6B active
- Context
- 262,144 tokens
- License
- NVIDIA Nemotron Open Model License
- Released
- 2025-12-15
- Vision
- No
→ GGUF (llama.cpp / LM Studio / Ollama) → MLX (Apple Silicon)
§1 Characteristics by quantization band
— Not yet rated · contributions welcome —
Q4–Q5 — 4–5 bit
24.7GB weights · e.g. Q4_K_M , mlx-4bit + KV: 48MB at 8K · 192MB at 32K · 768MB at 128Kdata checked Aug 2026
- quant-degradation-community — community consensus @ Q4_K_M · aggregated · 2026-08-30
Editorial derivation: one point down. This is the band to run — 24.7GB, and the tiny KV cache means a very long context stays affordable on top of it.
data checked Aug 2026
- quant-degradation-community — community consensus @ Q4_K_M · aggregated · 2026-08-30
Editorial derivation: one point down for 4-bit MoE experts on multi-step arithmetic.
data checked Aug 2026
- quant-degradation-community — community consensus @ Q4_K_M · aggregated · 2026-08-30
Editorial derivation: one point down from the full band.
data checked Aug 2026
- quant-degradation-community — community consensus @ Q6_K · aggregated · 2026-08-30
Editorial derivation: long-context retrieval is not quant-sensitive in the way arithmetic is, and 6-bit is near-lossless here. Carried unchanged.
data checked Aug 2026
- quant-degradation-community — community consensus @ Q6_K · aggregated · 2026-08-30
Editorial derivation: carried from the full band.
FP16 — full precision (fp16/bf16)
63.2GB weights · e.g. bf16 + KV: 48MB at 8K · 192MB at 32K · 768MB at 128Kdata checked Aug 2026
- vendor-model-card — RULER-100@1M = 86.3 @ bf16 · vendor-reported · 2026-08-30
92.9 at 256K and 91.3 at 512K. The best long-context evidence on this site by a wide margin — Gemma 4 31B, the nearest measured rival, manages 66.4% at 128K. RULER is a multi-hop, multi-needle test, not a single planted sentence, which is what makes the number meaningful.
data checked Aug 2026
- vendor-model-card — AIME25 = 89.1 @ bf16 · vendor-reported · 2026-08-30
GPQA 73.0, MMLU-Pro 78.3. Scored without tools; NVIDIA also reports 99.2 on AIME25 with tools, which measures the harness as much as the model.
data checked Aug 2026
- vendor-model-card — LiveCodeBench = 68.3 @ bf16 · vendor-reported · 2026-08-30
SWE-Bench (OpenHands): 38.8 — a long way below the competition-style number, and the honest signal for real repository work. This is not the coding model in this catalog.
data checked Aug 2026
- vendor-model-card — BFCL v4 = 53.8 @ bf16 · vendor-reported · 2026-08-30
Modest for a model marketed as agentic, and measured on BFCL v4 rather than the v3 most other entries here quote — not directly comparable.
data checked Aug 2026
- vendor-model-card — IFBench = 71.5 @ bf16 · vendor-reported · 2026-08-30
One of only eleven models on this site with any instruction-following evidence at all.
§2 Known issues & what fixes them
Quantizations below 4-bit are reported broken on this model, not merely degraded. The architecture is the reason: several tensor dimensions are not divisible by 128, so parts of the model cannot be quantized to lower bit widths at all — which is also why Q6_K (33.43GB) and Q8_0 (33.51GB) come out almost the same size.
Use Q4_K_M or better. The 3-bit build saves 5.7GB and costs far more than that in quality.
Evidence · 2 sources · community-consensus
- Quantizations below 4 bit are bad (other, 2026-08-30)
- NVIDIA Nemotron 3 Nano — how to run (quantization notes) (other, 2026-08-30)
LiveCodeBench 68.3 looks strong; SWE-Bench with OpenHands is 38.8. The gap between competition-style problems and real repository work is wide here, and the second number is the one that predicts whether it can fix your bug.
Pick it for long documents and reasoning, not for agentic coding. Ornith-1.5 35B-A3B and Qwen3.6 27B are the coding models at this footprint.
Evidence · 1 source · anecdotal
- Nemotron 3 Nano model card — LiveCodeBench 68.3 vs SWE-Bench 38.8 (vendor, 2026-08-30)
Released under the NVIDIA Nemotron Open Model License rather than Apache-2.0 or MIT. The weights are downloadable and commercial use is permitted, but it is a vendor licence with its own terms — read them before shipping something on top of it.
Not a defect. If a permissive licence is a hard requirement, Qwen3.6 35B-A3B (Apache-2.0) and Ornith-1.5 35B-A3B (MIT) are the comparable alternatives.
Evidence · 1 source · anecdotal
- NVIDIA Nemotron Open Model License (vendor, 2026-08-30)