GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
flashback2k
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
flashback2k
Model Tree
Qwen/Qwen3.6-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
q/k/v/o_proj, linear-attention in_proj_a/b/qkv/z + out_proj,
shared-expert gate/up/down_proj (routed experts untouched — 85% of weights)python
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "flashback2k/FlashModel-Qwen-3.6-35B-A3B-Maxed"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto") msgs = [ {"role": "system", "content": "You are a coding and reasoning assistant.\nreasoning_effort=high\nAdjust the depth of your reasoning to the level given above."}, {"role": "user", "content": "Напиши функцию бинарного поиска на Python."},]enc = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True)out = model.generate(enc["input_ids"].to(model.device), max_new_tokens=800)print(tok.decode(out[0][enc["input_ids"].shape[1]:], skip_special_tokens=True))The effort level is read from the system prompt:
text
<system>You are a coding and reasoning assistant.reasoning_effort=mediumAdjust the depth of your reasoning to the level given above.</system>| Value | Behaviour |
|---|---|
low | 1–2 sentences, minimal reasoning |
medium | short paragraph |
high | multi-paragraph reasoning |
xhigh | long trace, explores alternatives |
max | full chain-of-thought |
This was trained with matched-pairs data (same question at 5 effort levels), so the mapping is behavioural rather than a truncation of the same text.
| Metric | Baseline | Finetuned |
|---|---|---|
| Tool Use (8 scenarios) | 6/8 | 7/8 |
| Agentic (5 tasks) | 5/5 | 5/5 |
| Effort monotonic (low→max) | ❌ | ✅ |
| RU Perplexity | — | 5.41 |
Full benchmark suite (HumanEval, MBPP, GSM8K, MMLU, SWE-bench) is planned.
Apache-2.0, inherited from Qwen/Qwen3.6-35B-A3B.
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "flashback2k/FlashModel-Qwen-3.6-35B-A3B-Maxed"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto") msgs = [ {"role": "system", "content": "You are a coding and reasoning assistant.\nreasoning_effort=high\nAdjust the depth of your reasoning to the level given above."}, {"role": "user", "content": "Напиши функцию бинарного поиска на Python."},]enc = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True)out = model.generate(enc["input_ids"].to(model.device), max_new_tokens=800)print(tok.decode(out[0][enc["input_ids"].shape[1]:], skip_special_tokens=True))<system>You are a coding and reasoning assistant.reasoning_effort=mediumAdjust the depth of your reasoning to the level given above.</system>