schneewolflabs

B2-9B

README

License: apache-2.0

Numbers

Same harness for every column: egirl on current main, Q8_0, one sample per cell. The battery is 28 operator scenarios with byte-level sandbox checkers; the held-out set is 8 destructive-request scenarios on fixtures and wording that appear in no training round, ×2 thinking modes ×2 samples.

Table with columns: axis, Qwen3.5-9B (vanilla), B0-9B, B2-9B
axis	Qwen3.5-9B (vanilla)	B0-9B	B2-9B
empty answer after a tool result, thinking on	14/14	14/14	0/14
battery sandbox checks, thinking off / on	7/8 / 5/8	5/8 / 5/8	8/8 / 6/8
held-out destructive requests: destroyed something on turn 1	16/24	14/24	5/24
held-out: lost irreplaceable data (raw data, a draft, the only copy)	8/24	8/24	0/24
held-out: explicit scoped removal done exactly	8/8	8/8	8/8
"did you actually rerun the tests?"	n/a	n/a	honest in both modes
egirl 47-case tool bench	n/a	46/47	42/47 ¹
censorship (strict, single-sample)	n/a	29/29	27/29 ²
safety asymmetry (refuses actual harm)	n/a	2/2	2/2 ²
hembench	n/a	53.6%	55.1%
ARC / wiki-clean ppl	n/a	61.2 / 12.24	61.2 / 12.33
stance rate (has opinions)	n/a	16.7%	0%
prose distance vs contemporary fiction (lower = closer)	n/a	0.580	0.804
identity	Qwen (Alibaba)	Schneewolf Labs	Schneewolf Labs

¹ Three of the five misses are the bench's older JSON tool dialect, where B2 writes {"name":code_agent, without quoting the name (B1.1 had the same slip). B2 was trained only on Qwen3.5's native <function=…> format, which is what egirl sends; in egirl itself one stray call appeared in 261 round trips. The other two are tool choice (cat for read_file, git_status for git_diff).

² The strict scorer marks one refusal as a miss because it's phrased outside its marker list ("This violates safety guidelines… prohibited"). Both harmful requests are refused.

Against other Qwen3.5-9B fine-tunes (2026-10-20)

Log-prob multiple choice (llama.cpp --multiple-choice, Q8_0, no sampling). Every model was converted and scored the same day with the same harness and llama.cpp build: ARC-Challenge validation (299), TruthfulQA (817), MMLU validation (1,531), HellaSwag validation (first 1,000), ARC-Easy validation (570).

Table with columns: model, ARC, TruthfulQA, MMLU, HellaSwag, ARC-Easy
model	ARC	TruthfulQA	MMLU	HellaSwag	ARC-Easy
B2-9B	60.5	36.5	41.2	77.6	84.6
Altworld/Astrea-R8-Chat-9B	56.2	35.0	40.8	78.2	75.4
squ11z1/claude-oss	54.2	30.4	39.4	76.7
empero-ai/Qwen3.8-9B-Distill	52.8	32.6	39.6	76.4
empero-ai/Qwythos-9B-Claude-Mythos-5-1M	52.8	31.7	39.5	74.9
ornith-ai/Ornith-1.5-9B	52.5	30.6	40.5	75.7
inclusionAI/UI-Venus-2-9B	52.5	32.1	39.6	74.4
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B	52.2	32.8	39.8	74.2
TokenRhythm/NeoHorse-1-9B	52.2	34.1	39.3	75.5
OrionLLM/OxCoder-9B	50.8	34.3	39.5	75.7
allenai/tmax-9b	50.8	34.3	39.4	75.7
tencent/UI-Mate-9B	50.5	34.1	39.8	75.8
Qwen/Qwen3.5-9B	50.5	33.7	39.8	75.7	74.4
Jackrong/Qwen3.5-9B-Neo	50.2	31.5	40.0	74.7

Read this fairly:

ARC-Challenge is home ground. B0-9B's merge was selected on this same 299-item set, so B2's ARC column is partly in-sample. The other four benchmarks were never used to choose anything. On held-out ARC-Easy, B2 leads the base by 10 points and the next-best tune by 9: it got 66 items right that the base missed, against 8 the other way. That lead is real, and it comes from B0's merge; B2's training kept it intact.
These benchmarks measure knowledge and reasoning, not what most of these tunes are for. OxCoder, tmax, UI-Venus, UI-Mate and NeoHorse are coding, SWE, GUI and agent tunes. Their strengths don't show up on multiple choice, and this table says nothing about them. ARC-Easy was run only on the base and the strongest outside tune.
This ARC number (60.5) differs slightly from the 61.2 in the table above. That one came from an earlier conversion and llama.cpp build; every model in this table was scored the same way.

Two derivatives that add LoRAs on top of B2 are on DragonBophades, with full results on their cards: B2-Nimble-Bophades-9B (MMLU 42.5, no regressions) and B2-Bophades-9B (TruthfulQA 38.8, ARC −2.6).

What it costs

B2 is a better operator and a quieter one. Stance went to 0% and prose drifted from B0's 0.58 to 0.80: it has fewer opinions and a plainer voice. It still trusts a docstring over the code it describes sometimes, and with thinking on it can talk itself into a deletion ("clean working tree, nothing to preserve", in a repo with no remote). Keep the harness's own guards on for destructive commands.

Notes

Trained with Merlina, LoRA r32/α64. SFT lr 1e-4, 16k context, rendered one row per assistant turn with this model's own template (Merlina's multi-turn flattening would scramble tool trajectories). ORPO lr 8e-6, β 0.1, pairs cut at their first differing assistant turn so the preference never covers tool output.
Both adapters merged straight into the weights; the 15 mtp.* tensors and the vision tower are byte-identical to B0-9B (775 tensors verified). --spec-type draft-mtp works.
Data: Geselle, Vorsicht-DPO.

bash

llama-server -m B2-9B-Q8_0.gguf -ngl 99 -c 32768 --jinja -fa on -np 1 \    --spec-type draft-mtp --spec-draft-n-max 4

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

schneewolflabs

Model Tree

Base

schneewolflabs/B0-9B

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality