Javi0.4-2B-GGUF

GGUF quants of Javi0.4-2B, which is Javi0.3-2B with one embedding row changed. No fine-tuning, no new data, no gradients. The tied input/output row for token 51187 (=open_page) is multiplied by 0.84.

The edit biases one decision: after a failed lookup, call web_search again instead of opening a URL typed from memory. It does not add a new reasoning capability.

Measured effect

8 held-out eval-v3 canonical fail questions, first web_search forced to fail, greedy next tool:

model	next web_search	next open_page
Javi0.3-2B	0/8	8/8
Javi0.4-2B	7/8	1/8

This probe isolates the decision the edit targets. In a two-seed harness canary with real tools and sampling, 0.84 chose open_page after a permanently blocked search and completed, same as the base; it used one extra search on a normal lookup. A 0.75 scale flipped 4/4 but looped on 14 searches under a permanent block, so 0.84 is the conservative setting. The edit reaches the canonical open_page tool; in opencode/grok, webfetch/web_fetch after a 403 is unchanged.

Full eval v3

Measured on the bf16 safetensors model these quants come from; quantization adds its own small noise. 175 held-out seeds, 3 runs, date pin 2026-10-07, cached search results. Javi0.3-2B answers on the same seeds are the baseline. Judges: DeepSeek-V4.1-Flash-1017 and mimo-v26-dual.

metric	Javi0.3-2B	Javi0.4-2B
core pass (judge average)	0.35 [0.30, 0.40]	0.41 [0.36, 0.45]
core pass (deepseek)	0.48	0.58
core pass (mimo)	0.23	0.24
recovery after a tool failure	0.55 (n=11)	0.45 (n=10)
made-up links	0.01	0.00
loops	0.04	0.03

Paired core pass difference: +0.06 [0.02, 0.10] (deepseek +0.10 [0.05, 0.16], mimo +0.02 [-0.02, 0.06]), 95% bootstrap over 175 seeds. The deepseek interval clears zero; the mimo interval crosses zero, so the size of the gain is uncertain. Conflict questions improved (0.33 vs 0.07, n=7) and nodate (0.42 vs 0.17, n=6); premise (0.23 vs 0.29, n=13) and recovery after real failures did not.

Five answer episodes (4 seeds) carry no deepseek verdict because the judge omits the tools or style key; one seed never finished an episode in any of the three runs and the judge skips it, so judge-only rows cover 174 seeds. Core pass stays at 175 seeds with incomplete episodes scored 0. Full scoreboard: data/v2/eval/javi04-vs-03-2b/score.md in the source tree.

Files

File	Quant	Size	Notes
Javi0.4-2B.Q8_0.gguf	Q8_0	2.1 GB	Close to lossless
Javi0.4-2B.Q4_K_M.gguf	Q4_K_M	1.3 GB	Smaller and faster

Both were quantized from an F16 GGUF of the edited merged model. Text only: the base model's vision tower is not in the GGUF. F16 is available from the same conversion if you need it.

Run it

llama.cpp

llama-server -hf javierbits/Javi0.4-2B-GGUF:Q8_0 --jinja -c 131072 -fa on -ctk q8_0 -ctv q8_0 \
  --chat-template-kwargs '{"enable_thinking": false}' \
  --temp 0.2 --top-p 0.8 --top-k 20 --min-p 0

Point any OpenAI-compatible agent at http://localhost:8080/v1. Javi is built for agents with tools (web search, page fetch, a shell).

lmdeck

lmdeck use javi0.4-2b

• Thinking off. It was trained and evaluated with enable_thinking: false.
• Low temperature (0.2) keeps tool calls well formed.

Links

• Safetensors: Javi0.4-2B
• Base: Javi0.3-2B
• 4B control: Javi0.4-4B-GGUF
• Apache 2.0, inherited from Qwen3.5-2B.