Javi0.4-4B-GGUF (control)

GGUF quants of Javi0.4-4B, which is Javi0.3-4B with the =open_page embedding row scaled by 0.84. No fine-tuning, no new data, no gradients.

It exists as the 4B control for the Javi0.4 weight-space experiment: the same row edit applied to the larger model.

Measured effect

On 8 held-out eval-v3 canonical fail questions with the first web_search forced to fail, Javi0.3-4B already chose web_search in 4/4 cases, so that probe sees no change on 4B. On an opencode 403 replay, both models fetch another typed URL instead of searching again.

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. Javi0.3-4B answers on the same seeds are the baseline. Judges: DeepSeek-V4.1-Flash-1017 and mimo-v26-dual.

metric	Javi0.3-4B	Javi0.4-4B
core pass (judge average)	0.50 [0.45, 0.55]	0.56 [0.52, 0.61]
core pass (deepseek)	0.64	0.74
core pass (mimo)	0.36	0.39
recovery after a tool failure	0.58 (n=12)	0.75 (n=12)
made-up links	0.01	0.00
loops	0.03	0.02

Paired core pass difference: +0.06 [0.03, 0.10] (deepseek +0.10 [0.05, 0.14], mimo +0.04 [0.00, 0.07]), 95% bootstrap over 175 seeds. The deepseek interval clears zero; the mimo interval touches it. Conflict questions are the one category down (0.26 vs 0.40, n=7, directional at that n); unknowable questions are up (0.55 vs 0.32, n=10).

Two answer episodes (2 seeds, one per run) carry no deepseek verdict because the judge omits the tools or style key; both seeds are judged in the other runs, so the table covers 175 seeds. Incomplete episodes (7 across the three runs) are scored 0 for core pass and skipped by the judges. Full scoreboard: data/v2/eval/javi04-vs-03/score.md in the source tree.

This control measures slightly above Javi0.3-4B, but the targeted probe cannot attribute the gain to the open_page row alone. The 4B's remaining recovery gap in the webfetch/web_fetch route is untouched by the edit.

Files

File	Quant	Size	Notes
Javi0.4-4B.Q8_0.gguf	Q8_0	4.3 GB	Close to lossless
Javi0.4-4B.Q4_K_M.gguf	Q4_K_M	2.8 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.

Run it

llama.cpp

llama-server -hf javierbits/Javi0.4-4B-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

lmdeck

lmdeck use javi0.4-4b

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

Links

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