unsloth/Inkling-2-Small-GGUF

Run Inkling-2-Small via the Unsloth Desktop or read our Inkling 2 guide

See Unsloth Dynamic 3.0 GGUFs for our quantization benchmarks.

GGUF files

• UD-* folders: Unsloth Dynamic quants, imatrix-calibrated (imatrix_unsloth.gguf_file).
• BF16: lossless conversion: the original NVFP4 experts kept bit-exact (layers 0-39), every other weight BF16.
• UD-Q8_K_XL: the original NVFP4 experts kept bit-exact (layers 0-39), every other weight 8-bit.
• mmproj-BF16.gguf / mmproj-F16.gguf / mmproj-F32.gguf: vision projector, pass with --mmproj for image inputs.
• The chat template is embedded in every GGUF; use --jinja.

Quant	Size (GB)	Mean KLD vs BF16	99% KLD	Same top token
UD-IQ1_S	171.7	0.0922	1.143	89.7%
UD-IQ1_M	178.5	0.0829	1.041	90.2%
UD-IQ2_XXS	190.6	0.0577	0.730	91.8%
UD-Q2_K_XL	205.0	0.0450	0.559	92.7%
UD-IQ3_XXS	226.0	0.0364	0.430	93.3%
UD-Q3_K_XL	285.1	0.0176	0.209	95.3%
UD-Q4_K_XL	354.2	0.0029	0.031	98.0%
UD-Q8_K_XL	386.5	0.0027	0.029	98.1%
BF16	484.4	reference

KLD and top-token agreement are measured against the BF16 GGUF (the original NVFP4 experts kept as is, every other weight BF16) on 64 x 4096 tokens of wikitext-2, with llama.cpp's default F16 KV cache on both sides.

Running

Inkling 2 Small uses a new inkling2 architecture, so it needs a llama.cpp build with Inkling 2 support. Builds that only support the original Inkling will not load it.

1. Install llama.cpp with Inkling 2 support

Follow our Inkling 2 guide to set up llama.cpp with Inkling 2 support, or use the Unsloth Desktop app.

2. Download a quant and the vision projector

pip install -U huggingface_hub
hf download unsloth/Inkling-2-Small-GGUF \
    --include "UD-IQ2_XXS/*" "mmproj-F16.gguf" \
    --local-dir Inkling-2-Small-GGUF

Keep all shards in the same folder and pass the first one to llama.cpp; the rest load automatically.

3. Run

./llama.cpp/llama-server \
    -m Inkling-2-Small-GGUF/UD-IQ2_XXS/Inkling-2-Small-UD-IQ2_XXS-00001-of-00005.gguf \
    --mmproj Inkling-2-Small-GGUF/mmproj-F16.gguf \
    --jinja -ngl 99 -c 32768 \
    --temp 1.0 --top-p 1.0 --top-k 0 --min-p 0.0 \
    --chat-template-kwargs '{"reasoning_effort":"high"}'

Open http://localhost:8080 to chat and upload images. Lower -ngl if the model does not fit in VRAM, or use -ngl 0 for CPU inference. For text-only use, omit --mmproj. reasoning_effort accepts none, minimal, low, medium, high (default), xhigh and max (same as xhigh).

---

Inkling 2 Small

NVFP4 | MXFP8 | Playground | Tinker Cookbook | Acceptable Use

1. General Information

Inkling 2 Small is a general-purpose multimodal model that accepts text and image inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages. The model is designed to be used by developers building AI-powered applications, including agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation systems, and is suitable for general-purpose conversational use, instruction-following, and other natural language and visual tasks. It is released with open weights to support research, fine-tuning and integration into third-party products by downstream developers.

Languages: English, with general multilingual capabilities across other languages.

2. Getting Started

Try Inkling 2 Small on the Tinker Playground or access via API using the Tinker Cookbook. To fine-tune Inkling 2 Small with Tinker, also install the tml-renderers package.

Inkling 2 Small supports local inference using:

• SGLang (recipe)
• vLLM (recipe)
• TokenSpeed (recipe)
• Unsloth (recipe)

Inkling 2 Small can also be post-trained with:

• Miles
• SkyRL
• Snowflake Cortex Training

API access is also available through third party inference providers, including:

• NVIDIA
• Fireworks
• Together
• Baseten
• Nebius
• Modal
• Cloudflare

Required hardware

The model is distributed in two checkpoint formats.

The main NVFP4 checkpoint requires a GPU cluster with at least 500GB of aggregated VRAM. This can be met with either of the following example configurations:

• 2x NVIDIA B300 GPUs
• 4x NVIDIA H200 GPUs

The alternative MXFP8 checkpoint requires a GPU cluster with at least 800GB of aggregated VRAM. This can be met with either of the following example configurations:

• 4x NVIDIA B300 GPUs
• 8x NVIDIA H200 GPUs

The model was pretrained, midtrained and post-trained in NVFP4, so this is the native precision for the model. We recommend the NVFP4 checkpoint for all use-cases, and we're confident that it's the best option. The MXFP8 has a very marginal 1–2 percentage points gain over the NVFP4 checkpoint over evals, but we do not think it is meaningful for any practical use-cases.

Required software

Running the model directly on GPU hardware requires an inference deployment framework — either SGLang, vLLM, TokenSpeed, Unsloth, or Hugging Face, along with all of their respective dependency libraries.

3. Model Properties

Model type

Multimodal autoregressive transformer

Architecture type

A 48-layer decoder-only transformer with a sparse Mixture-of-Experts (MoE) feed-forward backbone: each token is routed to 8 of 384 experts. Attention is a hybrid of local and global layers. The model is natively multimodal — images are encoded via a vision transformer — with image and text inputs projected into a shared hidden space and processed jointly by the decoder.

Parameters

594B total, 17B active

Numerics support

MXFP8 and NVFP4

Input modalities

Inkling 2 Small accepts text input in UTF-8 encoding and image input in any pixel-based format (with each dimension ideally between 40px and 4096px for optimal performance). It supports a context window of up to 1M tokens.

Output modalities

Inkling 2 Small generates output as UTF-8 encoded text.

4. Training

Training data includes a broad variety of content types, including text, images, video. Training data for the model was drawn from publicly available sources, acquired from third-parties, generated internally, or synthetically generated or augmented. Publicly available data includes content from the public internet and publicly accessible repositories.

The training data curation process includes cleaning, processing, and modifying datasets. These processing steps, which vary by data type, may include deduplication and filtering to remove junk or other low-quality data, or to advance safety or other objectives.

5. Evaluations

	Open Weights Flash					Open Weights Pro					Closed Weights Flash
	Inkling 2 Small	GLM-5.3-Flash	MiMo V2.6 Flash	MiniMax-M3.1-Flash	DeepSeek-V4.1-Flash-1017	Muse Spark Open	GLM 5.3	MiMo V2.6 Pro	Mistral Large 4	Kimi K3	GPT-6 Luna	Gemini 3.8 Flash	Claude Haiku 5.5
Model Info
Params (B) activated / total	17/594	18/320	15/309	23/428	16/552	42/816	40/753	42/1020	49/1050	104/2800	–	–	–
Third Party Index
AA Index (v5.0)	30.6	27.8	26.7	29.1	32.6	24.9	31.7	29.9	26.1	–	27.9	30.8	36.5
Vals Index (v2.2)	56.1%	50.9%	54.8%	53.8%	61.3%	48.6%	59.7%	57.8%	56.5%	53.0%	52.3%	56.0%	58.7%
Coding
FrontierCode v2.0 stirrup v0.2.1	25.4%	17.6%	21.6%	20.8%	28.5%	7.6%	21.6%	24.0%	15.0%	17.3%	25.2%	18.7%	34.9%
DeepSWE v1.1 mini-swe-agent v2.4.6	72.1%	63.4%	67.9%	73.7%	77.0%	60.0%	69.0%	71.9%	61.7%	68.5%	66.6%	73.8%	59.9%
Terminal Bench Science v0.1 mini-swe-agent v2.4.6	5.7%	4.8%	4.3%	3.3%	12.9%	1.9%	9.5%	5.7%	4.3%	8.1%	8.6%	10.0%	20.0%
Vibe Code Bench v1.1 openhands (vals)	81.6%	30.8%	79.0%	73.9%	87.7%	76.2%	78.1%	85.2%	81.6%	85.0%	81.7%	78.7%	90.4%
SWE-Atlas v1.1 mini-swe-agent v2.4.6	61.9%	–	–	–	62.1%	42.3%	–	–	–	61.0%	50.8%	57.3%	59.4%
SWEBench Pro v2 (Hard) mini-swe-agent v2.4.6	86.3%	82.8%	89.7%	84.3%	89.7%	82.4%	84.3%	89.2%	83.8%	88.2%	88.7%	58.8%	52.9%
Sudo L7	14.1%	–	–	–	–	–	9.4%	–	13.9%	12.2%	–	10.6%	–
Autoresearch
PostTrainBench v1.2 Inkling 2 Small in Claude Code	31.9%	36.8%	–	–	30.5%	–	34.5%	–	–	31.5%	–	–	–
PMPP-Hard (AUC, 0–10h) pi v0.83.0	494.27	–	–	–	497.36	–	430.96	–	478.39	453.58	–	–	–
BioMysteryBench terminus v2	70.0%	–	69.3%	–	–	–	–	–	–	72.6%	61.5%	62.2%	70.4%
Search and Tools
BrowseComp Inkling 2 Small with compaction	90.2%	76.0%	78.1%	69.5%	87.8%	68.7%	75.1%	–	84.5%	88.4%	83.6%	89.4%	80.2%
DeepSearchQA Inkling 2 Small with compaction	90.9%	84.3%	86.0%	82.7%	84.5%	80.4%	84.7%	90.0%	84.4%	95.0%	83.5%	90.1%	83.2%
MCP Atlas Full / Public	85.4/85.0%	–/82.0%	–/62.9%	–/80.4%	–/83.2%	89.2/87.5%	84.2/83.6%	–/84.4%	–/84.5%	82.3/84.2%	–/77.8%	–/87.5%	–/81.0%
Knowledge Work
AA-Briefcase v1.1	1527	1451	1487	1476	1570	1279	1503	1512	1348	1497	1337	1203	1574
GDPVal-AA v2.1	1630	1649	1614	1465	1746	1401	1657	1689	1384	1543	1444	1445	1631
JobBench	70.5%	60.7%	61.2%	67.5%	68.5%	61.8%	61.4%	62.0%	55.2%	54.3%	49.0%	63.4%	39.2%
DAYJOB (Healthcare)	6.4%	1.2%	–	–	6.0%	–	4.4%	–	3.6%	4.0%	1.2%	2.0%	–
Enterprise Operations
EnterpriseOps-Gym	46.8%	33.2%	29.0%	48.9%	43.6%	43.1%	36.4%	38.0%	44.9%	45.3%	24.9%	45.7%	25.1%
EnterpriseBench-CoreCraft	71.8%	46.7%	–	–	58.5%	–	51.8%	–	47.7%	43.1%	43.1%	58.5%	–
Finance Work
Finance Agent v2.1	67.5%	60.6%	63.3%	58.8%	62.9%	60.7%	65.0%	64.3%	61.7%	60.0%	56.8%	65.8%	65.4%
Excel Modeling Benchmark v1.1	69.5%	66.3%	68.9%	67.8%	69.2%	62.0%	69.1%	67.4%	68.7%	71.3%	70.0%	72.9%	65.5%
Tax Agent Bench	65.8%	62.0%	59.9%	62.7%	74.9%	52.1%	73.1%	64.9%	67.5%	68.7%	58.9%	66.8%	62.2%
Apex-Accounting v1.1 pass@1	14.5%	12.3%	–	13.5%	12.5%	13.8%	13.9%	–	12.0%	9.5%	10.8%	15.5%	15.3%
DAYJOB (Finance)	14.3%	7.3%	–	–	12.5%	–	11.0%	–	4.8%	5.5%	6.8%	4.5%	–
DeepFinance	29.8%	–	–	–	–	–	27.5%	–	21.5%	–	26.4%	–	40.0%
Diligence Bench Best harness	58.1%	48.3%	–	51.6%	50.4%	59.0%	49.4%	51.8%	51.5%	50.9%	42.1%	51.1%	40.8%
AA-AnalystAgent	51.2%	25.0%	–	–	–	–	38.8%	37.5%	–	38.8%	43.8%	46.3%	53.8%
Tau 3 Banking v1.0.1	40.4%	47.2%	–	–	–	–	–	–	–	33.4%	–	–	–
ATLAS-Finance v1.1	6.0%	–	–	–	–	–	3.0%	–	–	3.7%	–	3.7%	–
Legal Work
Harvey LAB v1.1	21.7%	10.4%	13.3%	7.5%	14.2%	25.0%	14.6%	13.8%	15.8%	12.9%	4.2%	12.1%	4.2%
Legal Research Bench	46.6%	45.2%	38.0%	34.1%	45.2%	38.5%	49.0%	47.1%	35.6%	46.2%	30.3%	38.9%	43.8%
Visual Creation
DesignArena Web Apps	1286	–	–	–	–	–	1271	1274	–	1280	1160	1224	–
DesignArena Website	1331	1266	–	1275	1296	1300	1285	1303	1253	1330	1265	1295	1257
DesignArena Game Dev	1424	1270	–	1307	1261	1254	1292	1309	1218	1351	1254	1298	1314
DesignArena 3D Design	1457	1300	–	1319	1344	1255	1304	1322	1239	1367	1199	1279	1329
Code Arena (WebDev)	1653	1607	1637	1582	1665	–	1623	1625	1544	1656	1579	1583	1589
AA-3D	1021	937	–	–	–	–	782	977	–	982	–	965	994
Code2Video-AA	1020	975	1052	–	–	–	1034	1052	–	1041	1030	899	1192
BVB	71.6%	67.9%	–	–	70.0%	–	–	–	–	–	70.3%	65.9%	68.4%
Visual Perception
PerceptionBench	64.7%	49.6%	39.1%	47.1%	47.7%	44.1%	–	38.9%	46.5%	58.5%	56.2%	68.7%	60.5%
Humanity’s Sixth Sense	33.3%	26.8%	25.4%	–	30.1%	29.6%	–	25.2%	–	25.5%	21.0%	41.6%	–
BabyVision original / with Python	68.6/93.6%	53.4/84.0%	16.9/68.4%	56.1/91.0%	44.9/92.5%	44.3/80.2%	–	19.0/73.8%	42.3/71.0%	53.4/85.7%	55.3/79.6%	72.8/92.8%	48.3/93.9%
ScreenSpot Pro original / with Python	83.8/92.0%	–/85.3%	35.4/72.5%	48.5/76.8%	–	–	–	56.6/79.7%	42.3/43.4%	73.8/86.1%	81.1/87.7%	65.7/93.7%	85.4/88.7%
OmniDocBench v1.6	94.6%	92.3%	87.4%	92.0%	91.9%	93.8%	–	88.4%	90.2%	95.2%	92.3%	89.7%	92.6%
SimpleVQA with search and tools	68.2%	67.1%	–	–	–	63.6%	–	–	57.8%	68.5%	–	–	–
Visual Reasoning
GDP.pdf	25.2%	15.4%	9.0%	20.8%	17.2%	18.6%	11.2%	19.2%	17.6%	22.0%	22.8%	21.0%	20.8%
MMMU Pro Standard 10	81.6%	79.0%	67.8%	79.1%	80.6%	80.9%	–	74.1%	78.0%	80.5%	79.7%	85.6%	79.1%
Charxiv RQ original / with Python	85.6/89.1%	80.2/89.4%	66.2/88.4%	82.5/87.6%	77.0/89.6%	85.4/89.5%	–	74.2/86.7%	83.2/87.4%	84.8/91.3%	81.8/87.6%	86.2/92.4%	84.4/86.3%
Chartography original / with Python	36.7/82.1%	16.3/78.0%	7.5/73.9%	12.6%/–	17.9/83.0%	35.7/65.8%	–	10.8/69.0%	21.2/55.2%	26.6/66.6%	32.0/66.5%	40.9/81.0%	46.4/86.2%
VIALS original / with stirrup v0.2.1	34.6/57.8%	–/53.0%	–	–/49.7%	–/53.2%	–	–	–/58.4%	–/42.0%	20.9%/–	–/44.1%	–/52.0%	–/60.5%
SAGE v1.1	88.6%	89.3%	83.3%	85.3%	–	85.8%	–	84.4%	74.2%	86.8%	83.4%	88.2%	89.8%
MuirBench	79.2%	71.6%	63.2%	69.4%	75.7%	74.5%	–	72.6%	67.5%	77.0%	73.9%	80.1%	74.0%
ZeroBench (main) original / with Python	29.0/44.0%	13.0/32.0%	7.0%/–	21.0%/–	23.0%/–	14.0/50.0%	–	8.0%/–	15.0/23.0%	23.0/41.0%	16.0%/–	23.0%/–	23.0%/–
STEM Reasoning
CritPt v2 Full / Hard	55.7/35.0%	–/24.5%	–/29.5%	51.4/32.5%	50.6/25.0%	52.6/29.5%	57.4/33.5%	56.9/34.0%	50.3/27.0%	–/40.5%	65.1/42.5%	65.1/46.5%	64.0/43.5%
HLE-Diamond	28.7%	18.2%	13.7%	28.1%	25.3%	26.3%	17.9%	15.2%	17.3%	26.9%	22.2%	33.1%	29.6%
HLE (text only)	44.1%	39.9%	35.1%	48.0%	43.3%	43.9%	42.3%	49.4%	36.4%	46.9%	38.5%	47.8%	44.4%
ArxivMath 10/2026	27.7%	–	–	–	38.3%	19.2%	–	–	18.1%	–	–	–	–
BrokenArxiv 10/2026	63.3%	–	–	–	49.7%	33.3%	–	–	30.6%	–	–	–	–
ARC-AGI-1	96.5%	91.0%	–	–	93.5%	89.0%	–	–	–	94.5%	86.7%	98.5%	89.0%
ARC-AGI-2	81.7%	65.8%	–	–	78.1%	57.5%	–	–	–	60.4%	59.3%	89.2%	61.3%
MysteryMechanism	25.2%	–	21.6%	–	–	–	23.0%	15.3%	–	–	19.4%	36.5%	35.1%
Long Context
AA-LCR v1.1	83.3%	80.0%	74.3%	79.7%	82.7%	78.3%	79.7%	86.3%	78.0%	88.7%	83.3%	81.3%	82.7%
LongBench v2	70.6%	68.2%	60.7%	60.9%	69.0%	68.7%	68.4%	68.0%	65.7%	69.0%	65.0%	73.7%	65.3%
Factuality
AA-Omniscience v1.1 score	16.1	0.7	-10.8	-6.4	0.9	25.8	6.0	-4.5	5.1	–	-8.3	23.3	12.3
AA-Omniscience v1.1 non-hallucination rate	73.3%	61.7%	47.8%	6.3%	35.9%	72.0%	61.1%	39.8%	71.8%	–	20.7%	44.9%	65.8%
Instruction Following
ComplexConstraints v1.0	44.5%	27.6%	22.1%	23.2%	50.4%	41.3%	30.5%	32.3%	36.5%	37.9%	27.3%	48.4%	36.8%
Multilinguality
Global-MMLU-Lite	91.0%	89.0%	83.9%	78.5%	90.4%	91.2%	89.8%	88.0%	88.0%	90.6%	90.2%	93.2%	87.8%
MDPBench	81.4%	70.9%	54.7%	69.2%	68.8%	82.0%	–	67.0%	64.3%	83.6%	71.2%	81.5%	78.4%
Safety
HoneyBench v0.2 (↓)	52.6%	–	–	–	76.4%	85.6%	76.8%	–	83.6%	78.5%	–	80.5%	–
DistressBench	82.0%	72.7%	–	–	–	87.7%	72.5%	–	77.0%	73.5%	66.7%	70.7%	71.7%
FORTRESS (adversarial)	83.8%	73.3%	64.7%*	47.9%	72.8%	92.4%	71.8%	69.9%*	76.0%	73.4%	89.2%	79.5%*	90.5%
FORTRESS (benign)	79.7%	96.4%	97.4%*	96.8%	93.1%	84.0%	96.8%	97.1%*	91.8%	97.3%	92.4%	94.8%*	91.0%
StrongREJECT (none)	97.1%	97.8%	97.8%	97.4%	99.4%	97.1%	97.5%	99.0%	99.0%	99.0%	99.4%	93.0%	97.8%
Cybersecurity
CyberBench v1.1	72.7%	67.9%	75.4%	–	–	–	72.1%	72.9%	–	75.2%	76.3%	43.8%	75.5%
PatchEval	79.6%	74.8%	77.0%	76.5%	80.4%	77.8%	69.6%	80.0%	76.1%	77.0%	76.5%	77.8%	81.7%

Best reported score in each row (lowest where lower is better); equal displayed scores tie Second-best reported score in each row; none when first place is tied

* On public split only.

For ScreenSpot Pro evaluation, images whose long side exceed 4,096 pixels are downsampled to that limit while preserving the aspect ratio; the ground truth answers were rescaled accordingly. Smaller images remain unchanged.

6. Safety

We conducted safety evaluations ahead of release, spanning both everyday human-AI interaction and dangerous-capability testing. Because Inkling 2 Small is multimodal, we paid attention to whether safety behavior held consistently across text and image inputs. We applied mitigations to reduce risks before release.

For everyday interaction, we evaluated sycophancy, harmful manipulation, and psychological-harm patterns like parasocial dependency and validation of delusional reasoning, including through multi-turn, open-ended external red-teaming designed to surface issues that only emerge over longer conversations. We also assessed whether the model refuses genuinely harmful requests without over-refusing benign ones. For CBRN and cyber, we assessed knowledge and procedural uplift through internal evaluations, external testing, and refusal-suppressed variants intended to estimate latent capability with safeguards removed. For loss of control, we evaluated agentic capability, strategic deception, and sabotage potential, benchmarked against public frontier models, and found the model materially below frontier capabilities.

Across all areas, we concluded that Inkling 2 Small did not present risk of material uplift beyond what's already available in the open-weight ecosystem.

7. Bias, risks and limitations

Inkling 2 Small may exhibit general limitations common to foundation models, including hallucination (generating plausible but factually incorrect or unsupported content), occasional failures to follow instructions precisely, and degraded performance in long multi-turn conversations. As with other large-scale models trained on web-derived and synthetic data, Inkling 2 Small may reflect biases present in its training data, including demographic, cultural, or linguistic biases, and may perform unevenly across languages, dialects, or subject domains that were less represented during training.

Inkling 2 Small's knowledge is limited to information available as of its training cutoff, and it may not reflect events, developments, or changes that occurred afterward.

We recommend that downstream developers and deployers apply appropriate human oversight and review for outputs used in high-stakes or safety-critical contexts, rather than relying on Inkling 2 Small's outputs without verification.

• Conduct their own evaluation of Inkling 2 Small's performance, safety, and fairness for their specific use case, language, and population prior to deployment, particularly for applications involving vulnerable groups.
• Implement additional safeguards — such as content filtering, rate limiting, and monitoring — at the application layer, especially for open deployment contexts where Inkling 2 Small's built-in mitigations may not be sufficient on their own.
• Avoid deploying Inkling 2 Small in domains such as medical, legal, or safety-critical decision-making without additional fine-tuning, domain-specific validation, and human oversight.

8. Legal

Training Data Documentation