Monitor: show Ollama's loaded models, their VRAM footprint, and busy state

The status snapshot now queries /api/ps (2s timeout so a wedged Ollama
cannot stall the channel) and the ollama line renders e.g.
'UP · llama3.1:8b (4.8 GiB VRAM) · busy'; comfy gets the busy marker
too while an image job runs.

cmd/gpu-turnstile/main.go

@@ -813,7 +813,7 @@ func run(ctx context.Context, cfg config.Config, log *slog.Logger, logOut io.Wri
 	// AUTO_UPDATE.
 	if isService {
 		serveControl(ctx, log, u, exePath, applyStaged,
-			statusProvider(cfg, lk, comfySup, health, started, gw),
+			statusProvider(cfg, lk, comfySup, health, started, gw, ollamaClient),
 			reloadHandler(cfg, configPath, restartWhenIdle))
 	}
 
@@ -1106,6 +1106,16 @@ type statusDownstream struct {
 	URL     string `json:"url"`
 	Up      bool   `json:"up"`
 	Managed string `json:"managed,omitempty"`
+	// Models lists Ollama's loaded models with their VRAM footprint. Null
+	// when unknown (query failed / not applicable); [] means none loaded —
+	// deliberately no omitempty so the two stay distinguishable.
+	Models []statusModel `json:"models"`
+}
+
+// statusModel is one loaded Ollama model.
+type statusModel struct {
+	Name   string `json:"name"`
+	VRAMMB int64  `json:"vram_mb"` // 0 = resident in RAM, not VRAM
 }
 
 type statusLock struct {
@@ -1183,8 +1193,10 @@ func diffConfig(a, b config.Config) []string {
 	return out
 }
 
-// statusProvider assembles the one-line JSON snapshot for CmdStatus.
-func statusProvider(cfg config.Config, lk *lock.Lock, comfySup *supervise.Process, health *healthTracker, started time.Time, gw *gpuWatch) func() string {
+// statusProvider assembles the one-line JSON snapshot for CmdStatus. The
+// loaded-model query to Ollama gets a short timeout so a wedged upstream
+// cannot stall the status channel for long.
+func statusProvider(cfg config.Config, lk *lock.Lock, comfySup *supervise.Process, health *healthTracker, started time.Time, gw *gpuWatch, ollamaClient *ollama.Client) func() string {
 	return func() string {
 		snap := statusSnapshot{
 			Version: version,
@@ -1197,9 +1209,21 @@ func statusProvider(cfg config.Config, lk *lock.Lock, comfySup *supervise.Proces
 			Foreign: foreign, AgeS: ageS,
 		}
 		if cfg.OllamaURL != "" {
-			snap.Downstreams = append(snap.Downstreams, statusDownstream{
+			d := statusDownstream{
 				Name: "ollama", URL: cfg.OllamaURL, Up: health.get("ollama"),
-			})
+			}
+			if ollamaClient != nil {
+				mctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
+				models, err := ollamaClient.LoadedModelDetails(mctx)
+				cancel()
+				if err == nil {
+					d.Models = make([]statusModel, 0, len(models))
+					for _, m := range models {
+						d.Models = append(d.Models, statusModel{Name: m.Name, VRAMMB: m.SizeVRAM / (1024 * 1024)})
+					}
+				}
+			}
+			snap.Downstreams = append(snap.Downstreams, d)
 		}
 		if cfg.ComfyURL != "" {
 			d := statusDownstream{Name: "comfy", URL: cfg.ComfyURL, Up: health.get("comfy")}

cmd/gpu-turnstile/monitor.go

@@ -188,7 +188,9 @@ func renderMonitor(snap statusSnapshot, width int) string {
 	b.WriteString(cDim + " " + strings.Repeat("─", width-2) + cReset + "\x1b[K\n")
 
 	for _, d := range snap.Downstreams {
-		b.WriteString(renderDownstream(d) + "\x1b[K\n")
+		busy := (d.Name == "ollama" && snap.Lock.State == "llm" && snap.Lock.LLMInflight > 0) ||
+			(d.Name == "comfy" && snap.Lock.State == "image")
+		b.WriteString(renderDownstream(d, busy) + "\x1b[K\n")
 	}
 	b.WriteString("\x1b[K\n")
 	b.WriteString(renderLock(snap.Lock) + "\x1b[K\n")
@@ -227,25 +229,46 @@ func renderGPU(g statusGPU) string {
 	return s
 }
 
+// formatMB renders MiB as "4.2 GiB" (or MiB below 1 GiB).
+func formatMB(mb int64) string {
+	if mb >= 1024 {
+		return fmt.Sprintf("%.1f GiB", float64(mb)/1024)
+	}
+	return fmt.Sprintf("%d MiB", mb)
+}
+
 // renderVRAM renders "4.2 / 16.0 GiB used" (or MiB below 1 GiB).
 func renderVRAM(used, total int) string {
-	format := func(mb int) string {
-		if mb >= 1024 {
-			return fmt.Sprintf("%.1f GiB", float64(mb)/1024)
-		}
-		return fmt.Sprintf("%d MiB", mb)
-	}
 	if total > 0 {
-		return format(used) + " / " + format(total) + " used"
+		return formatMB(int64(used)) + " / " + formatMB(int64(total)) + " used"
 	}
-	return format(used) + " used"
+	return formatMB(int64(used)) + " used"
 }
 
 // printableLen counts characters without ANSI escapes (ASCII-only content).
 func printableLen(s string) int { return len(s) }
 
-func renderDownstream(d statusDownstream) string {
+func renderDownstream(d statusDownstream, busy bool) string {
 	url := cDim + d.URL + cReset
+	detail := ""
+	if d.Models != nil {
+		if len(d.Models) == 0 {
+			detail = cDim + " · no models loaded" + cReset
+		} else {
+			parts := make([]string, 0, len(d.Models))
+			for _, m := range d.Models {
+				if m.VRAMMB > 0 {
+					parts = append(parts, fmt.Sprintf("%s (%s VRAM)", m.Name, formatMB(m.VRAMMB)))
+				} else {
+					parts = append(parts, m.Name+" (in RAM)")
+				}
+			}
+			detail = " · " + strings.Join(parts, ", ")
+		}
+	}
+	if busy {
+		detail += " · " + cCyan + "busy" + cReset
+	}
 	switch d.Managed {
 	case "stopped":
 		return fmt.Sprintf(" %s○%s %-8s %sstopped (managed — starts on demand)%s  %s",
@@ -259,7 +282,7 @@ func renderDownstream(d statusDownstream) string {
 		suffix = " (external)"
 	}
 	if d.Up {
-		return fmt.Sprintf(" %s●%s %-8s %sUP%s%s   %s", cGreen, cReset, d.Name, cGreen, cReset, suffix, url)
+		return fmt.Sprintf(" %s●%s %-8s %sUP%s%s%s   %s", cGreen, cReset, d.Name, cGreen, cReset, suffix, detail, url)
 	}
 	return fmt.Sprintf(" %s●%s %-8s %sDOWN%s %s", cRed, cReset, d.Name, cRed, cReset, url)
 }

cmd/gpu-turnstile/monitor_test.go

@@ -47,6 +47,25 @@ func TestRenderMonitor(t *testing.T) {
 			t.Errorf("frame missing %q:\n%s", want, frame)
 		}
 	}
+
+	snap.Downstreams[0].Models = []statusModel{{Name: "llama3.1:8b", VRAMMB: 4900}, {Name: "embed", VRAMMB: 0}}
+	snap.Lock = statusLock{State: "llm", LLMInflight: 1}
+	frame = renderMonitor(snap, 80)
+	for _, want := range []string{"llama3.1:8b (4.8 GiB VRAM)", "embed (in RAM)", "busy"} {
+		if !strings.Contains(frame, want) {
+			t.Errorf("frame missing %q:\n%s", want, frame)
+		}
+	}
+
+	snap.Downstreams[0].Models = []statusModel{}
+	snap.Lock = statusLock{State: "idle"}
+	frame = renderMonitor(snap, 80)
+	if !strings.Contains(frame, "no models loaded") {
+		t.Errorf("frame missing %q:\n%s", "no models loaded", frame)
+	}
+	if strings.Contains(frame, "busy") {
+		t.Errorf("idle lock still shows busy:\n%s", frame)
+	}
 }
 
 func TestFmtDur(t *testing.T) {

internal/ollama/client.go

@@ -60,13 +60,21 @@ func (c *Client) Probe(ctx context.Context) error {
 
 type psResponse struct {
 	Models []struct {
-		Name  string `json:"name"`
-		Model string `json:"model"`
+		Name     string `json:"name"`
+		Model    string `json:"model"`
+		SizeVRAM int64  `json:"size_vram"` // bytes resident in VRAM (0 = RAM-only)
 	} `json:"models"`
 }
 
-// LoadedModels returns the names of models currently held in memory.
-func (c *Client) LoadedModels(ctx context.Context) ([]string, error) {
+// LoadedModel is one model currently held in memory.
+type LoadedModel struct {
+	Name     string
+	SizeVRAM int64 // bytes resident in VRAM; 0 when the model sits in RAM
+}
+
+// LoadedModelDetails returns the models currently held in memory with
+// their VRAM footprint.
+func (c *Client) LoadedModelDetails(ctx context.Context) ([]LoadedModel, error) {
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, c.base+"/api/ps", nil)
 	if err != nil {
 		return nil, err
@@ -84,13 +92,26 @@ func (c *Client) LoadedModels(ctx context.Context) ([]string, error) {
 	if err := json.NewDecoder(resp.Body).Decode(&ps); err != nil {
 		return nil, err
 	}
-	models := make([]string, 0, len(ps.Models))
+	models := make([]LoadedModel, 0, len(ps.Models))
 	for _, m := range ps.Models {
-		if m.Name != "" {
-			models = append(models, m.Name)
-		} else {
-			models = append(models, m.Model)
+		name := m.Name
+		if name == "" {
+			name = m.Model
 		}
+		models = append(models, LoadedModel{Name: name, SizeVRAM: m.SizeVRAM})
+	}
+	return models, nil
+}
+
+// LoadedModels returns the names of models currently held in memory.
+func (c *Client) LoadedModels(ctx context.Context) ([]string, error) {
+	details, err := c.LoadedModelDetails(ctx)
+	if err != nil {
+		return nil, err
+	}
+	models := make([]string, 0, len(details))
+	for _, m := range details {
+		models = append(models, m.Name)
 	}
 	return models, nil
 }