Ollama 경로

# office, 2026-09-15, Ollama 0.34.0 (Homebrew, launchd). The -mlx tag selects Ollama's MLX engine.
ollama show qwen3.8:27b-mlx | head -8      # architecture qwen3_5, 27.8B, quantization nvfp4
ollama show qwen3.8:latest  | head -8      # architecture qwen35,  27.3B, quantization Q4_K_M

ollama run qwen3.8:27b-mlx --verbose "Explain unified memory in 150 words." >/dev/null
# load duration:        3.64s
# prompt eval count:    21 token(s)
# prompt eval rate:     13.59 tokens/s      <- the first forward touching every page (previous lesson)
# eval count:           305 token(s)
# eval rate:            43.23 tokens/s      <- above the physics track's 44 ceiling? read on
ollama ps
# NAME               ID            SIZE   PROCESSOR  CONTEXT  UNTIL
# qwen3.8:27b-mlx    5642e97495e1  18 GB  100% GPU   131072   Forever

# the runner's own accounting (Ollama.app writes ~/.ollama/logs/server.log; this launchd install logs to ~/Library/Logs)
grep "speculative decode stats" ~/Library/Logs/ollama.err.log | tail -1
# msg="speculative decode stats" iterations=225 drafted=458 accepted=287 acceptance=0.63 avg_draft=2.04 max_draft=4
#   -> 512 tokens in 225 passes through the weights: 2.3 tokens per pass, 45 ms per pass (217-225 over four runs)

# the GGUF engine drafts with the same head, and the community benchmark on the same blob does not:
grep -E "MTP draft|draft acceptance" ~/Library/Logs/ollama.err.log | tail -2
# common_speculative_init_result: creating MTP draft context against the target model ...
# slot print_timing: draft acceptance = 0.86695 ( 2906 accepted /  3352 generated), mean len =  4.47
./llama.cpp/build/bin/llama-bench -m ~/.ollama/models/blobs/sha256-<the qwen3.8:latest blob> -p 512 -n 128 -ngl 99
# | qwen35 27B Q4_K - Medium | 15.65 GiB | 27.32 B | MTL,BLAS | tg128 | 26.39 ± 0.44 |

#!/usr/bin/env python3
"""Stream from the Ollama API and time the tokens yourself. eval_count / eval_duration
is the daemon's own rate; first-chunk-to-done is the wall clock. They should agree.
What neither tells you is how many passes through the weights produced them —
that is in the runner's log."""
import json, time, urllib.request


def run(model: str, prompt: str, n: int = 512) -> None:
    body = {"model": model, "prompt": prompt, "stream": True, "think": False,
            "options": {"num_predict": n, "temperature": 0, "seed": 1}}
    req = urllib.request.Request("http://127.0.0.1:11434/api/generate", data=json.dumps(body).encode(),
                                 headers={"Content-Type": "application/json"})
    first = None
    with urllib.request.urlopen(req, timeout=900) as resp:
        for line in resp:
            d = json.loads(line)
            if d.get("done"):
                last = d
                break
            first = first or time.perf_counter()
    wall = time.perf_counter() - first
    ec, ed = last["eval_count"], last["eval_duration"] / 1e9
    print(f"{model}: {ec} tokens  reported {ec/ed:.1f} tok/s  wall {ec/wall:.1f} tok/s  "
          f"(load {last['load_duration']/1e9:.2f}s, prompt {last['prompt_eval_duration']/1e9:.2f}s)")


for p in ("Explain unified memory in 400 words.",
          "Repeat this sentence exactly 40 times, one per line: The quick brown fox jumps over the lazy dog."):
    run("qwen3.8:27b-mlx", p)

# office, 2026-09-15, four prose runs: reported 47.57 / 47.60 / 49.33 / 50.62; wall 47.79 / 47.98 / 49.63 / 50.93
# repetition (384 tokens): wall 90.2 and 91.0 tok/s -- acceptance 1.00, 4.9 tokens per pass in the runner log
# the ceiling for 14.45 GB per token at 638 GB/s is 44: every number above it is more than one token per pass