GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
llmfan46
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
llmfan46
Model Tree
Base
empero-ai/Qwythos-9B-Claude-Mythos-5-1M
Fine-tuned
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Creating these models takes significant time, work and compute. If you find them useful consider supporting me:
| Platform | Link | What you get |
|---|---|---|
| 🎉 Patreon | Monthly support | Priority model requests |
| ☕ Ko-fi | One-time tip | My eternal gratitude |
Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.
| Parameter | Value |
|---|---|
| direction_index | 20.52 |
| attn.out_proj.max_weight | 1.74 |
| attn.out_proj.max_weight_position | 29.99 |
| attn.out_proj.min_weight | 1.02 |
| attn.out_proj.min_weight_distance | 24.58 |
| mlp.down_proj.max_weight | 1.98 |
| mlp.down_proj.max_weight_position | 19.18 |
| mlp.down_proj.min_weight | 1.65 |
| Metric | This model | Original model (Qwythos-9B-Claude-Mythos-5-1M) |
|---|---|---|
| KL divergence | 0.0123 | 0 (by definition) |
| Refusals | ✅ 11/100 | ❌ 73/100 |
Original:
============================================================
Total questions: 7021
Correct: 5408
Accuracy: 0.7703 (77.03%)
Parse failures: 0
============================================================
Tested subject scores:
Heretic:
============================================================
Total questions: 7021
Correct: 5431
Accuracy: 0.7735 (77.35%)
Parse failures: 0
============================================================
Tested subject scores:
MMLU - Massive Multitask Language Understanding, multiple-choice questions across 57 subjects (math, history, law, medicine, etc.).
GGUF quantizations available here llmfan46/Qwythos-9B-Claude-Mythos-5-1M-uncensored-heretic-GGUF.
Developed by Empero
Qwythos-9B is a full-parameter reasoning model built on top of a deeply uncensored Qwen3.5-9B base and post-trained on over 500 million tokens of high-quality Claude Mythos and Claude Fable traces, with chain-of-thought generated in-house by Empero AI's internal tool rethink.
The result is a compact, fast, dramatically more capable 9B reasoning model. Headline capabilities:
Qwythos is intentionally uncensored. It is designed to engage seriously with technically demanding questions across cybersecurity, red-teaming methodology, biology, pharmacology, and clinical medicine — domains where over-aligned models tend to refuse, hedge into uselessness, or surface boilerplate disclaimers in place of substance.
Same harness. Same sampling. Same prompts. The wins are real.
| Task | Metric | Base Qwen3.5-9B | Qwythos-9B | Δ |
|---|---|---|---|---|
| gsm8k | exact_match (flexible) | 0.670 | 0.860 | +0.190 |
| gsm8k | exact_match (strict) | 0.510 | 0.810 | +0.300 |
| mmlu | acc | 0.232 | 0.575 |
All numbers produced with lm-evaluation-harness, HF backend, --apply_chat_template, Qwen3.5 sampling (temperature=0.6, top_p=0.95, top_k=20), --limit 100. Full per-task and per-subject (MMLU) breakdown in evals/lm_eval_results.md. Raw results*.json and per-sample samples_*.jsonl are available on request.
The MMLU +34.3 lift is the headline. Qwythos posts 0.575 mean across all 57 subjects, peaking at 0.78 on government/politics, 0.77 on college biology, 0.74 on conceptual physics — placing it well above what most 9B reasoning models deliver under the same evaluation conditions. Absolute MMLU numbers for any 9B model are sensitive to harness, few-shot count, and chat-template handling; what matters in this comparison is that both models were evaluated with identical settings.
Qwythos supports OpenAI/Qwen3.5-style function calling out of the box — no extra wrapper, no fine-tune-on-tools needed. Pass tools=[...] to the chat template and the model emits valid <tool_call> blocks per Qwen3.5's spec, with required parameters honored.
We evaluated tool use on a 7-prompt harness combining capability demos with deliberately hard factual-recall prompts where closed-book sampling fails:
| Prompt | Tool selected | Outcome |
|---|---|---|
Compute sin(π/7) × cos(π/11) to 10 dp | python_executor | ✅ 0.4163083990 (correct, single call) |
| Count primes below 100,000 | python_executor | ✅ 9592 (correct, wrote and ran a sieve) |
| Latest stable CPython 3 release | web_search | ✅ Found 3.14.6 (June 2026), 3.15 in beta, cited source |
7 of 7 succeeded. Tool selection was always sensible (math → Python; facts → search). The four bottom rows are particularly important: they are the four hardest specialty facts to recall closed-book — and Qwythos, given the right tools, searched, integrated multiple sources, and produced source-cited correct answers in every case.
Full transcripts with the model's reasoning, every tool call issued, every result returned, and the final integrated answer are in evals/tool_test_outputs.md.
This makes Qwythos deployment-ready for retrieval-augmented agentic settings, where the model verifies its specifics rather than fabricating them.
Qwythos ships with YaRN rope-scaling configured by default for a 1,048,576-token (≈1M) context window — a 4× extension over the 262,144-token native architecture. The configuration is baked into config.json and applies automatically at load time; no separate flag, post-processing step, or YaRN-specific tokenizer is required:
json
"rope_parameters": {"rope_type": "yarn","factor": 4.0,"original_max_position_embeddings": 262144,"mrope_interleaved": true,"mrope_section": [11, 11, 10],"rope_theta": 10000000},"max_position_embeddings": 1048576
This is the official Qwen3.5 recipe for 1M context, matching the configuration documented in Qwen's own model card and the vLLM/SGLang deployment recipes. Long-context inference was validated on this checkpoint via in-house smoke testing at ~137k tokens.
What 1M context unlocks:
<think> reasoning over multi-paper biomedical or pharmacological corpora.Serving at 1M:
bash
# vLLMvllm serve empero-ai/Qwythos-9B-Claude-Mythos-5-1M --max-model-len 1010000# SGLangSGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server \--model-path empero-ai/Qwythos-9B-Claude-Mythos-5-1M --context-length 1010000
Practical notes:
rope_parameters.rope_type to "default" from the included config.json.pre_yarn backup.The harness is a small ~150-line Python file:
python_executor(code) — runs Python in a subprocess (12s timeout, captured stdout/stderr)web_search(query, max_results) — DuckDuckGo via the ddgs packagePass both as tools= to apply_chat_template and parse <tool_call> blocks from the model's output. The parser handles Qwen3.5's chat-template format:
markdown
<tool_call><function=NAME><parameter=PARAM>value</parameter></function></tool_call>
Empero will release the reference harness on GitHub.
Qwythos was trained as a reasoning model and inherits Qwen3.5's thinking-mode behavior. Use these settings as defaults:
python
gen_kwargs = dict(do_sample=True,temperature=0.6, # Qwen3.5 thinking-mode recommendedtop_p=0.95,top_k=20,repetition_penalty=1.05,max_new_tokens=16384, # generous budget for the <think> reasoning block + final answer)
Why these: in a controlled retest (see evals/retest_outputs.md), we evaluated multiple sampling configurations against the three most-difficult factual prompts. Greedy decoding and very-low-temperature sampling (T≤0.3) degenerated into repetition loops — a known failure mode for reasoning models on this class of prompts. Qwen3.5's recommended setting (T=0.6) cleanly avoids this and delivers the best factual reliability we measured: across the three retest prompts, zero of the six errors flagged in closed-book review recurred at T=0.6 — including the safety-relevant physostigmine claim, the misattributed CVE, and the incorrect hashcat hash-mode.
Use repetition_penalty=1.05 — a small deviation from Qwen's default of 1.0 that prevents rare non-terminating reasoning loops on long generations.
Qwythos is a general-purpose reasoning model with explicit emphasis on cybersecurity, biomedical, and quantitative reasoning. From the qualitative sample-generations review across 25 prompts spanning these domains (full transcripts in evals/sample_generations.md):
python_executor when invoked.The uncensored base means Qwythos engages substantively with these prompts rather than refusing, hedging, or burying answers in disclaimer boilerplate. Reasoning is shown in the <think> block; final answer follows.
Qwen/Qwen3.5-9B — a dense, natively multimodal architecture with a hybrid attention stack (3:1 Gated DeltaNet linear-attention to Gated full-attention), ~152k vocabulary, long native context.config.json. Native architectural context is 262,144 tokens; YaRN factor 4.0 extends this to the full 1M window without any retraining or runtime flag, matching Qwen's official long-context recipe.Qwythos was post-trained on over 500 million tokens of high-quality reasoning data drawn from:
rethink, Empero AI's internal CoT-generation tool. rethink produces deliberately structured <think>-block reasoning that walks through hypothesis, verification, and conclusion before the final answer is committed — directly shaping Qwythos's reason-then-answer behavior.All data was normalized to Qwen3.5's chat format. Training used assistant-only loss so the model is scored only on completion tokens.
Full-parameter supervised fine-tuning with TRL:
| Hyperparameter | Value |
|---|---|
| Schedule | 2-phase curriculum: broad reasoning corpus → focused agentic + coding |
| Effective batch size | 16 |
| Max sequence length | 128,000 (no truncation) |
| Learning rate | 1e-5 → 5e-6 cosine across phases |
| Optimizer | paged AdamW (8-bit) |
| Precision | bf16 |
| Loss | chunked NLL, assistant-only |
Held-out validation loss decreased monotonically across both phases (final eval_loss ≈ 0.709, mean token accuracy 0.799 on a curated holdout). No overfitting observed.
The base is multimodal; for text-only inference load with AutoModelForImageTextToText:
python
import torchfrom transformers import AutoModelForImageTextToText, AutoTokenizermodel_id = "empero-ai/Qwythos-9B-Claude-Mythos-5-1M"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForImageTextToText.from_pretrained(model_id, dtype="bfloat16", device_map="auto")messages = [{"role": "user","content": "Walk through the biochemistry of how organophosphate nerve agents inhibit acetylcholinesterase, the resulting cholinergic toxicity, and the medical antidotes."}]text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tok(text, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=16384, do_sample=True,temperature=0.6, top_p=0.95, top_k=20, repetition_penalty=1.05,)# Output opens with <think>...</think> reasoning, then the final answer.print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
python
TOOLS = [{"type": "function", "function": {"name": "python_executor","description": "Execute Python code and return stdout.","parameters": {"type": "object","properties": {"code": {"type": "string"}},"required": ["code"]}}},{"type": "function", "function": {"name": "web_search","description": "Search the web for current facts and citations.","parameters": {"type": "object","properties": {"query": {"type": "string"},"max_results": {"type": "integer"}},"required": ["query"]}}},]text = tok.apply_chat_template(messages, tools=TOOLS, tokenize=False, add_generation_prompt=True)# ... then parse <tool_call><function=...><parameter=...>...</parameter></function></tool_call> blocks
Requirements: a recent transformers (Qwen3.5 support) plus the Gated DeltaNet kernels (flash-linear-attention and a CUDA-matched causal_conv1d build) — without them the linear-attention layers fall back to slow, memory-hungry PyTorch ops.
Qwythos is a focused 9B reasoning model. A few characteristics are worth knowing to get the best out of it:
<think> block before the final response. Allow generous max_new_tokens (16,384 recommended) and parse/strip the <think>...</think> span for end users.temperature=0.6, top_p=0.95, top_k=20, repetition_penalty=1.05 for consistently crisp results.Sign up for the Empero newsletter at empero.org for releases, evals, and research notes on Qwythos and future open-weight models from the lab.
If this model helped you, consider supporting the project:
bc1qx6zepu6sfkvshgdmc4ewu6pk6rpadvpgffpp7vltc1qv2mefzps2vtjcpwfx8xxdrpplrcvltswm68r7x42Dbm5xg5Nq26fdyzfEU7KBnAJfhi7Cvz5J2ex5CzHXkfKuNEJzYCcmJ1GTbgjFZ5MBx72sdG1G9239Cd6rsZfv4QeDkYJYWeights are released under Apache-2.0, inherited from the Qwen3.5-9B base. Shared for research and experimentation, as-is.
| mlp.down_proj.min_weight_distance | 11.05 |
| attn.o_proj.max_weight | 1.98 |
| attn.o_proj.max_weight_position | 23.72 |
| attn.o_proj.min_weight | 0.76 |
| attn.o_proj.min_weight_distance | 13.31 |
| arc_challenge | acc | 0.470 | 0.490 | +0.020 |
| arc_challenge | acc_norm | 0.400 | 0.410 | +0.010 |
| gpqa_diamond (CoT, 0-shot) | exact_match (flexible) | 0.630 | 0.580 | −0.050 |
| Hashcat mode for Kerberos TGS-REP | web_search | ✅ -m 13100 with 4 corroborating sources |
| CVE for PrintNightmare | web_search | ✅ CVE-2021-34527 (and correctly distinguished from CVE-2021-1675 / CVE-2021-34481 variants) |
| Is physostigmine indicated for organophosphate poisoning? | web_search | ✅ "NOT indicated — would be harmful. Physostigmine is for the anticholinergic toxidrome." Cited LITFL toxicology. |
| DPP-4 cleavage site in GLP-1 / semaglutide modification | web_search | ✅ Ala⁸–Glu⁹ cleavage, α-aminoisobutyric acid (Aib) at position 8 in semaglutide — cited Wikipedia and pharma source |