GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
zime-ai
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
zime-ai
Model Tree
Qwen/Qwen3-4B-Instruct-2507
Input Modalities
Output Modalities
Supported Functionality
| Dwight 4B 1.0 | |
|---|---|
| Base model | Qwen3-4B-Instruct-2507 (Apache 2.0) |
| Context | 32,768 tokens |
| Decisions | one-token answers with calibrated probabilities |
| Insights | JSON with heading, detail, grade, score, timestamp and a verbatim excerpt |
| Hardware | one 24-80 GB GPU (bf16, ~8 GB of weights); best with vLLM |
| License | Apache 2.0 |
One question in, one token out, with a calibrated confidence. Asked about the same call again, each further question costs a few hundredths of a second.
Accuracy vs Jev (313 questions on 120 held-out calls, labels set by an independent LLM referee; the same questions for both models):
| Question | Dwight 4B | Jev 1.13 |
|---|---|---|
| Next meeting set (High / Medium / Low) | 0.79 (macro-F1 0.79) | 0.57 (macro-F1 0.39) |
| Pricing sentiment (low / mid / high) | 0.86 | 0.74 |
| Competitor discussed (High / Medium / Low) | 0.66 (macro-F1 0.64) | 0.65 (macro-F1 0.57) |
| Objection raised and unresolved (yes / no) | 0.64 | 0.79 |
At scale (tens of thousands of questions on sales calls, agreement with a large frontier model's answers on the same calls): next meeting 0.80, competitor 0.76, objections 0.75, pricing 0.76, with calibration error (ECE) 0.02-0.05.
Speed (one NVIDIA H100, vLLM, bf16; Jev and GLM 5 through their APIs):
| ~20-minute call | Dwight 4B | Jev 1.13 | GLM 5 |
|---|---|---|---|
| First question | 0.13 s | 0.34 s (all questions in one request) | 1.9 s |
| Each further question on the same call | 0.02 s | (included above) | 1.9 s |
On longer calls Dwight's first question takes 0.54 s at ~60 minutes (20k tokens) and 1.06 s at
~90 minutes (33k tokens); further questions stay under 0.08 s, because vLLM keeps the
transcript cached (enable_prefix_caching=True).
Structured, quotable insights: what was said, when, how strong the signal is, and the exact words. Compared with GLM 5 on identical inputs (475 call checklists across 40 held-out calls from 4 companies; the reference is a large frontier model's answer on the same calls):
| Dwight 4B | GLM 5 | |
|---|---|---|
| Quotes found verbatim in the transcript | 100% | 98.7% |
| Grade agrees with the reference | 83% | 72% |
| Its insights the reference also reports | ~57% | ~44-56% |
| Reference insights it also finds | ~50% | ~61% |
| Median time per checklist | 4.2 s (one H100) | 12 s (API) |
On one H100, 4 checklists at a time, Dwight writes about 2,000 checklists an hour. It is precise and faithful to the transcript, and more conservative than larger models: it reports fewer insights.
One month at 10,000 calls, each with 10 decision questions and 10 insight checklists (100,000 decisions and 100,000 insights):
| Per month | Dwight 4B, self-hosted | GLM 5 (API) | Frontier API model | Jev (API) |
|---|---|---|---|---|
| 100,000 decisions | ~$5 | ~$1,000 | ~$1,750 | ~$5-10 |
| 100,000 insights | ~$200 | ~$1,970 | ~$6,940 | not offered |
| Total | ~$205 | ~$2,970 |
How these are built: Dwight on one H100 billed per second at about 3.95anhour(about1GPUhourforthedecisions,about50fortheinsights;theGPUisoffwhenidle).GL2,900 a month and only pays off at much higher volume.
Dwight answers one question at a time with one token. Put the transcript and the question in this layout (letters A, B, C... map to your options in order):
text
system: You are a sales decision model. Read the conversation and answer the question with exactly one option token. user:<conversation>[00:00:05] [Maya Brooks]: Can we meet Tuesday at 10?[00:00:09] [Dan Ruiz]: Tuesday 10 works, I'll send the invite.</conversation> <question id="next_meeting_set" type="choice">Was a concrete next meeting agreed, with a date and time?</question>Options:A) HighB) MediumC) LowAnswer with exactly one letter.For a yes/no question use type="boolean" and end with Answer yes or no.; for a 0-10 score
use type="score" with options A) 0 ... K) 10. Read the probabilities of the option tokens
from the first generated token and renormalize over them: that is the confidence.
See examples/decide.py (vLLM, about 40 lines).
Questions are yours to write: any question a reader could answer from the call works best when it is specific and states what counts as each option.
Give the transcript after a short description of what to look for, and ask for JSON. See
examples/insights.py. Output shape:
json
{"details": [{"heading": "Next meeting set for Tuesday", "detail": "The buyer agreed to a follow-up on Tuesday at 10:00 and the rep will send the invite.", "grade": "High", "score": 90, "timestamp": "00:00:09", "excerpt": "Tuesday 10 works, I'll send the invite."}], "summary": "A follow-up meeting was agreed for Tuesday at 10:00."}When nothing qualifies, Dwight answers with a single detail headed "No insights found as per checklist".
One line per turn: [HH:MM:SS] [Speaker name]: text for decisions,
text
[HH:MM:SS] Speaker name: textGGUF quantizations for llama.cpp, LM Studio and Ollama, made by bartowski (thank you!): bartowski/zime-ai_dwight-4b-GGUF, from BF16 (8.05 GB) down to IQ2_M (1.49 GB).
bash
ollama run hf.co/bartowski/zime-ai_dwight-4b-GGUF:Q5_K_MIn LM Studio, search for zime-ai_dwight-4b and pick Q5_K_M.
Using the confidence scores? Use Q5_K_M or higher. Decisions read the probabilities of the option tokens, and quantization shifts those probabilities before it changes the answers. The quantizations were calibrated on a general text corpus, not on sales calls. For insights and plain answers without confidence, Q4_K_M (2.59 GB) is a good default.
Fine-tuned from Qwen3-4B-Instruct-2507 with LoRA on 8 NVIDIA H100 GPUs, on about 35,000 sales-call insight examples covering 500+ call behaviors, plus about 8,000 decision questions, from synthetic B2B software sales calls. The training data is not released.
| Version | Notes |
|---|---|
| 1.0 | First release |
Apache 2.0. See LICENSE and NOTICE. Built on Qwen3-4B-Instruct-2507 by the Qwen team.
Zime is an AI platform for sales teams: it analyzes every sales call, coaches reps and surfaces what moves deals forward. Dwight is built from what Zime learned analyzing real sales conversations. Learn more at zime.ai.
bibtex
@misc{dwight4b2026, title = {Dwight 4B: straight answers about sales calls}, author = {Zime AI}, year = {2026}, url = {https://huggingface.co/zime-ai/dwight-4b}, note = {https://zime.ai}}| decisions only |
system: You are a sales decision model. Read the conversation and answer the question with exactly one option token.user:<conversation>[00:00:05] [Maya Brooks]: Can we meet Tuesday at 10?[00:00:09] [Dan Ruiz]: Tuesday 10 works, I'll send the invite.</conversation><question id="next_meeting_set" type="choice">Was a concrete next meeting agreed, with a date and time?</question>Options:A) HighB) MediumC) LowAnswer with exactly one letter.[HH:MM:SS] Speaker name: text{"details": [{"heading": "Next meeting set for Tuesday", "detail": "The buyer agreed to a follow-up on Tuesday at 10:00 and the rep will send the invite.", "grade": "High", "score": 90, "timestamp": "00:00:09", "excerpt": "Tuesday 10 works, I'll send the invite."}], "summary": "A follow-up meeting was agreed for Tuesday at 10:00."}ollama run hf.co/bartowski/zime-ai_dwight-4b-GGUF:Q5_K_M@misc{dwight4b2026, title = {Dwight 4B: straight answers about sales calls}, author = {Zime AI}, year = {2026}, url = {https://huggingface.co/zime-ai/dwight-4b}, note = {https://zime.ai}}