Downloads · 30 days
63
9% of all-time downloads
MrFadiAi/Qwen3.6-35B-A3B-Hermes-V6
Qwen3.6-35B-A3B-Hermes-V6 is a image-text-to-text model from MrFadiAi. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for gguf. The card lists the license as apache-2.0.
A mixture-of-experts, multimodal (vision-language) model with a Hermes-style agentic / function-calling alignment, distributed as a compact GGUF for llama.cpp / llama-server.
Downloads · 30 days
63
9% of all-time downloads
All-time downloads
682
Public
Repo size
18.3 GB
Likes
2
Public
Click a slice to open those files.
.gguf18.3 GB · 100%
From the Hugging Face model README
A mixture-of-experts, multimodal (vision-language) model with a Hermes-style agentic / function-calling alignment, distributed as a compact GGUF for llama.cpp / llama-server.
In the author's local 8-model benchmark suite, this build placed #1 in every category — math, knowledge, and agentic tool-use — making it the top composite scorer of the set.

📊 The full interactive report is also bundled in this repo:
FINAL_REPORT.html.
| Base lineage | Qwen 3.6 family (community build / fine-tune — not an official Alibaba release) |
| Architecture | Mixture-of-Experts (MoE), Qwen3 |
| Total / active params | ~35B total / ~3B active per token (the A3B notation) |
| Modality | Text + Vision (ships with a separate mmproj multimodal projector) |
| Alignment | Hermes V6 — agentic, function-calling, instruction-tuned |
| Format | GGUF — APEX-Compact mixed-precision (~4 bpw-class) |
| Main file size | ~17 GB |
| Serving | llama.cpp / llama-server (OpenAI-compatible API) |
The MoE design is the key to its efficiency: although ~35B parameters are loaded, only ~3B are active on any given token, so it runs at usable speeds on consumer APUs/GPUs while keeping dense-model quality.
| File | Size | Description |
|---|---|---|
Qwen3.6-35B-A3B-Hermes-V6-APEX-Compact.gguf | ~17 GB | Main model weights (APEX-Compact GGUF). Load this with llama-server -m. |
Qwen3.6-35B-A3B-Hermes-V6-mmproj.gguf | ~858 MB | Multimodal projector (vision encoder adapter). Load with --mmproj. Required for image input. |
FINAL_REPORT.html | ~13 KB | Interactive benchmark report (champion board + full breakdown). |
Measured by the author on local hardware (see Methodology & caveats below). This model is 🥇 #1 in the 8-model comparison.
| Model | Size | GSM8K (math) | Knowledge | Agentic | Composite | Speed |
|---|---|---|---|---|---|---|
| 🥇 Qwen3.6-35B-Hermes-V6 (this) | 16.2 GB | 91.0% | 78.1% | 90.0% | 86.4% | ~15 t/s |
| 🥈 Gemma-4-31B | 8.0 GB | 84.0% | 73.4% | 90.0% | 82.5% | 6.5 t/s |
| 🥉 Gemma-4-12B-QAT | 6.3 GB | 88.5% | 75.2% | 80.0% | 81.2% | 10.6 t/s |
| Benchmark | Score |
|---|---|
| ARC-Challenge | 93.0% |
| HellaSwag | 85.5% |
| OpenBookQA | 94.5% |
| BoolQ | 89.5% |
| Winogrande | 75.0% |
| TruthfulQA | 31.0% |
| Knowledge average | 78.1% |
lm-evaluation-harness (industry standard).⚠️ TruthfulQA is low for every model in this set (25–31%). TruthfulQA is adversarial by design; these subsampled, locally-judged scores are not directly comparable to official leaderboard figures.
llama-server \
-m Qwen3.6-35B-A3B-Hermes-V6-APEX-Compact.gguf \
--mmproj Qwen3.6-35B-A3B-Hermes-V6-mmproj.gguf \
-ngl 99 \
-c 32768 \
--port 8080 \
--host 0.0.0.0
Then talk to it like any OpenAI API at http://localhost:8080/v1/chat/completions.
The Hermes V6 alignment supports the standard OpenAI tools schema (tool_choice: auto). Example:
curl -s http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
"model": "Qwen3.6-35B-A3B-Hermes-V6-APEX-Compact.gguf",
"messages": [{"role":"user","content":"Find my pending order and cancel only that one."}],
"tools": [ /* your function schemas */ ],
"tool_choice": "auto",
"temperature": 0.1
}'
This is a hybrid reasoning model. Prefix the system prompt with /no_think for fast, non-reasoning responses (recommended for high-volume tool-calling / agent loops); omit it to engage chain-of-thought reasoning.
With the --mmproj projector loaded, you can pass images (via the llama-server multimodal interface) alongside text for image-understanding tasks.
These results are author-measured on a specific local setup, not official leaderboard scores. Be aware:
lm-evaluation-harness (EleutherAI) — the industry-standard harness.Full details and the interactive charts are in FINAL_REPORT.html.
MrFadiAi. It is not an official Alibaba / Qwen or Nous Research / Hermes product.license: apache-2.0 field follows the upstream Qwen3 lineage. Verify and comply with the applicable upstream Qwen license for your use case before redistribution or commercial deployment.Built on the outstanding work of the Qwen team, the Hermes alignment tradition, the llama.cpp project, and EleutherAI's lm-evaluation-harness.