GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
fatsam13
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
fatsam13
Model Tree
Qwen/Qwen3-VL-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
adapter_model.safetensors: v2 PEFT weightsadapter_config.json: rank 8, alpha 16 PEFT configurationbeforeat-food-nutrition-vision-lora-v2-f16.gguf: v2 F16 llama.cpp adapterblend_metadata.json: reproducible v2 weight-interpolation metadatabeforeat-food-nutrition-vision-lora-f16.gguf: historical v1 GGUF releaseOnly one adapter is loaded at runtime. The v1 file remains available for rollback; new integrations should use the versioned v2 file.
Dish recognition:
text
Identify the dish in this image. Reply with only the exact Food-101 class name.
Experimental visible ingredients and portions:
text
Estimate the visible ingredients and their portions in grams. Reply only with a JSON array of objects using keys "name" and "grams".
| Task | Evaluation | Result |
|---|---|---|
| Food-101 dish recognition | 500-image held-out set, strict | 438/500 (87.60%) |
| Food-101 dish recognition | Alias/near matching | 440/500 (88.00%) |
| Visible ingredients | Nutrition5k, 100 images | 44.51% mean recall |
| Matched ingredient portions | Nutrition5k, 100 images | 52.93% mean recall |
| Matched ingredient grams | Nutrition5k, 85 parsed rows | 43.34 g MAE |
The previous food-only release scored 434/500 (86.80%) strict and 438/500 (87.60%) with aliases on the same Food-101 evaluation.
The ingredient/portion results are experimental and should not be interpreted as direct nutrition accuracy. Hidden ingredients, cooking oils, recipe details, and true serving mass cannot be reliably recovered from one image.
The v2 weights are a linear interpolation between the 2,500-step Food-101 LoRA
and the continued 4,000-step ingredient/portion LoRA. The nutrition checkpoint
weight is 0.25. Both inputs use the same rank, alpha, tensor names, and target
modules, producing a single 504-tensor LoRA adapter.
816q_proj, k_proj, v_proj, o_proj, gate_proj,
up_proj, down_projQwen/Qwen3-VL-4B-InstructQwen3-VL-4B-Instruct-UD-Q4_K_XL.ggufunsloth/Qwen3-VL-4B-Instruct-GGUFmmproj-F16.gguf from the same base GGUF repository1.000fa7cb284cbf133fc426733bd64238a3588a33e50433065152 bytesConversion command:
bash
PYTHONPATH=tools/llama.cpp \python tools/llama.cpp/convert_lora_to_gguf.py \adapters/qwen3vl4b_food_nutrition_blend_w025 \--base models/Qwen3-VL-4B-Instruct-bf16-remapped \--outfile adapters/qwen3vl4b_food_nutrition_blend_w025/beforeat-food-nutrition-vision-lora-v2-f16.gguf \--outtype f16 \--verbose
Runtime command:
bash
llama-mtmd-cli \-m Qwen3-VL-4B-Instruct-UD-Q4_K_XL.gguf \--mmproj mmproj-F16.gguf \--image food.jpg \--lora-scaled beforeat-food-nutrition-vision-lora-v2-f16.gguf:1.0 \-p "Identify the dish in this image. Reply with only the exact Food-101 class name." \--jinja --temp 0 -n 16 -c 4096 --image-min-tokens 1024
Validation used the same command with
markdown
--device none -ngl 0 --no-mmproj-offload --no-op-offload --no-kv-offload --fit off
UD-Q4_K_XL base and its existing mmproj-F16.gguf are compatible and reusable.
| Expected | PyTorch/PEFT v2 | Base GGUF | GGUF + v2 LoRA |
|---|---|---|---|
| prime rib | prime rib | roast beef | prime rib |
| bread pudding | panna cotta | dessert | panna cotta |
| chocolate cake | chocolate mousse | Chocolate Cake | chocolate mousse |
The matching PEFT and GGUF+LoRA predictions demonstrate conversion fidelity, including the same errors.
ac31fb420d91fd8a4149e694c4da540db6208889c53f86b383069a6422a01f62